NTHU - CVLab | Publications

Journal Papers
Local Journal Papers
Conference Papers
Patents
Book Chapters

Journal Papers
1. GAN-Based Day-to-Night Image Style Transfer for Nighttime Vehicle Detection
  - Che-Tsung Lin, Sheng-Wei Huang, Yen-Yi Wu, Shang-Hong Lai
  - IEEE Transactions on Intelligent Transportation System 22(2): 951-963 (2021)
2. Learning to Match Ground Camera Image and UAV 3-D Model-Rendered Image Based on Siamese Network With Attention Mechanism
  - W. Liu, C. Wang, X. Bian, S. Chen, S. Yu, X. Lin, SH Lai, D. Weng, J. Li
  - IEEE Geoscience and Remote Sensing Letters 17(9): 1608-1612 (2020)
3. Multi-task CNN for restoring corrupted fingerprint images
  - Wei Jing Wong, Shang-Hong Lai
  - Pattern Recognition
4. Real-time Single-Stage Vehicle Detector Optimized by Multi-Stage Image-based Online Hard Example Mining
  - Che-Tsung Lin, Shu-Ping Chen, Patrisia Sherryl Santoso, Hung-Jin Lin, Shang-Hong Lai
  - IEEE Transactions on Vehicular Technology, vol.69, no.2, pp.1505-1518, 2020-02
5. AE-GAN-Net: Learning Invariant Feature Descriptor to Match Ground Camera Images and a Large-Scale 3D Image-Based Point Cloud for Outdoor Augmented Reality
  - W. Liu, C. Wang, X. Bian, S. Chen, Wei Li, X. Lin, Y. Li, D. Weng, SH Lai, J. Li
  - Remote. Sens. 11(19): 2243 (2019)
6. Image captioning by incorporating affective concepts learned from both visual and textual components
  - Jufeng Yang, Yan Sun, Jie Liang, Bo Ren, Shang-Hong Lai
  - Neurocomputing Volume 328, 7 February 2019, Pages 56-68
7. Relationship between sonography of sternocleidomastoid muscle and cervical passive range of motion in infants with congenital muscular torticollis
  - Chu-HsuLin, Hung-ChihHsu, Yu-Jen Hou, Kai-Hua Chen, Shang-Hong Lai, Wen-Ming Chang
  - Biomedical Journal, pp. 1-7, Jan. 2019
8. Real-time video stitching.
  - Shuo-Han Yeh, Shang-Hong Lai
  - IEEE International Conference on Image Processing, Beijing, China.
9. Video synthesis from stereo videos with iterative depth refinement.
  - C.-H. Wei, S.-H. Lai, C.-K. Chiang
  - Journal of Visual Communication and Image Representation, Vol. 47, pp. 48-61, Aug. 2017
10. A multi-attribute sparse coding approach for action recognition from a single unknown viewpoint
  - T.-F. Su, C.-K. Chiang, and S.-H. Lai
  - IEEE Transactions on Circuits and Systems for Video Technology, 26(8), 1476-1489, Aug. 2016
11. Multi-scale energy optimization for object proposal generation
  - C. Wang, J. Yang, K. Wang, and S.-H. Lai
  - Multimedia Tools and Applications, 2016, 1-19, May 2016
12. A Multi-Attribute Sparse Coding Approach for Action Recognition from A Single Unknown Viewpoint
  - T.-F. Su, C.-K. Chiang, and S.-H. Lai
  - IEEE Transactions on Circuits and Systems for Video Technology , Vol. PP, Issue: 99
13. A Joint Learning Approach to Face Detection in Wavelet Compressed Domain
  - S.-H. Huang and S.-H. Lai
  - Mathematical Problems in Engineering, Vol. 2014, Article ID 548791
14. A novel gradient attenuation Richardson–Lucy algorithm for image motion deblurring
  - H.-L. Yang, P.-H. Huang, and S.-H. Lai
  - Signal Processing, Vol. 103, pp. 399–414, Oct. 2014
15. Automatic Facial Expression Exaggeration System with Parallelized Implementation on a Multi-Core Embedded Computing Platform
  - T.-F. Su, C.-H. Duan, S.-F Wang, Y.-T. Lee, and S.-H. Lai
  - Journal of Signal Processing Systems, Vol. 75, Issue 2 , pp. 155-168, May 2014
16. Guest editorial: Advances in 3D video processing
  - S.-H. Lai
  - Journal of Visual Communication and Image Representation, Vol. 25, Issue 4, pp. 597–598, May 2014
17. Spatio-Temporally Consistent View Synthesis from Video-Plus-Depth Data with Global Optimization
  - H.-A. Hsu, C.-K. Chiang, and S.-H. Lai
  - IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Vol.24, No. 1, pp. 74-84, Jan 2014
18. Automatic Distortion Correction of Endoscopic Images Captured With Wide-Angle Zoom Lens
  - T.-Y. Lee, T.-S. Chang, C.-H. Wei, S.-H. Lai, K.-C. Liu, and H.-S. Wu
  - IEEE Transactions on Biomedical Engineering (TBME), Vol.60, no.9, pp.2603-2613, Sep. 2013
19. Face Verification With Local Sparse Representation
  - C.-H. Duan, C.-K. Chiang, and S.-H. Lai
  - IEEE SIGNAL PROCESSING LETTERS, Vol. 20, No. 2, pp. 177-180, Feb. 2013
20. Learning Component-Level Sparse Representation for Image and Video Categorization
  - C.-K. Chiang, C.-H. Liu, C.-H. Duan, and S.-H. Lai
  - IEEE Transactions on Image Processing (TIP),Vol. 22, No. 12, pp. 4475-4787, Dec. 2013
21. Learning spatial weighting for facial expression analysis via constrained quadratic programming
  - C.-T. Liao, H.-J. Chuang, C.-H. Duan , and S.-H. Lai
  - Pattern Recognition, Vol. 46, No. 11, pp. 3103-3116, Nov. 2013
22. A Flexible PCB Inspection System Based on Statistical Learning
  - C.-T. Liao, W.-H. Lee, and S.-H. Lai
  - Journal of Signal Processing Systems, Vol. 67, Issue 3, pp. 279-290, June 2012 (bibtex)
  - @article{DBLP:journals/vlsisp/LiaoLL12,
    author = {Chia-Te Liao and
    Wen-Hao Lee and
    Shang-Hong Lai},
    title = {A Flexible PCB Inspection System Based on Statistical Learning},
    journal = {Signal Processing Systems},
    volume = {67},
    number = {3},
    year = {2012},
    pages = {279-290},
    ee = {http://dx.doi.org/10.1007/s11265-010-0556-8},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
23. Parallelization of belief propagation on cell processors for stereo vision
  - K.-Y. Hsieh, C.-H. Lai, S.-H. Lai, and J. K. Lee
  - ACM Transactions on Embedded Computing Systems (TECS), Vol. 11S, Issue 1, Article No. 13, June 2012 (bibtex)
  - @article{DBLP:journals/tecs/HsiehLLL12,
    author = {Kun-Yuan Hsieh and
    Chi-Hua Lai and
    Shang-Hong Lai and
    Jenq Kuen Lee},
    title = {Parallelization of Belief Propagation on Cell Processors
    for Stereo Vision},
    journal = {ACM Trans. Embedded Comput. Syst.},
    volume = {11},
    number = {S1},
    year = {2012},
    pages = {13},
    ee = {http://doi.acm.org/10.1145/2180887.2180889},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
24. Robust kernel-based learning for image-related problems
  - C.-T. Liao and S.-H. Lai
  - Image Processing, IET, Vol. 6, Issue 6, pp. 795 - 803, Oct. 2012
25. A learning-based contrarian trading strategy via a dual-classifier model
  - S.-H. Huang, S.-H. Lai, and S.-H. Tai
  - ACM Transactions on Intelligent Systems and Technology (TIST), Vol.2 , Issue 3, Article No. 20, April 2011 (bibtex)
  - @article{DBLP:journals/tist/HuangLT11,
    author = {Szu-Hao Huang and
    Shang-Hong Lai and
    Shih-Hsien Tai},
    title = {A learning-based contrarian trading strategy via a dual-classifier
    model},
    journal = {ACM TIST},
    volume = {2},
    number = {3},
    year = {2011},
    pages = {20},
    ee = {http://doi.acm.org/10.1145/1961189.1961192},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
26. A novel robust kernel for visual learning problems
  - C.-T. Liao and S.-H. Lai
  - Neurocomputing, Vol. 74, No. 5, pp. 708-719, Feb. 2011 (bibtex)
  - @article{DBLP:journals/ijon/LiaoL11,
    author = {Chia-Te Liao and
    Shang-Hong Lai},
    title = {A novel robust kernel for visual learning problems},
    journal = {Neurocomputing},
    volume = {74},
    number = {5},
    year = {2011},
    pages = {708-719},
    ee = {http://dx.doi.org/10.1016/j.neucom.2010.09.009},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
27. An Orientation Inference Framework for Surface Reconstruction from Unorganized Point Clouds
  - Y.-L. Chen and S.-H. Lai
  - IEEE Transactions on Image Processing, Vol. 20, Issue 3, pp.762-775, Mar. 2011 (bibtex)
  - @article{DBLP:journals/tip/ChenL11,
    author = {Yi-Ling Chen and
    Shang-Hong Lai},
    title = {An Orientation Inference Framework for Surface Reconstruction
    From Unorganized Point Clouds},
    journal = {IEEE Transactions on Image Processing},
    volume = {20},
    number = {3},
    year = {2011},
    pages = {762-775},
    ee = {http://dx.doi.org/10.1109/TIP.2010.2076297},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
28. Bipartite Polar Classification for Surface Reconstruction
  - Y.-L. Chen, T.-Y. Lee, B.-Y. Chen and S.-H. Lai
  - Computer Graphics Forum, Vol. 30, no. 7, pp. 2003-2010, Sep. 2011 (Proceedings of Pacific Graphics 2011). (bibtex)
  - @article{DBLP:journals/cgf/ChenLCL11,
    author = {Yi-Ling Chen and
    Tung-Ying Lee and
    Bing-Yu Chen and
    Shang-Hong Lai},
    title = {Bipartite Polar Classification for Surface Reconstruction},
    journal = {Comput. Graph. Forum},
    volume = {30},
    number = {7},
    year = {2011},
    pages = {2003-2010},
    ee = {http://dx.doi.org/10.1111/j.1467-8659.2011.02039.x},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
29. Compressibility-Aware Media Retargeting with Structure Preserving
  - S.-F. Wang and S.-H. Lai
  - IEEE Transactions on Image Processing, Vol. 20, No. 3, pp. 855-865, March 2011. (SCI, EI) (bibtex)
  - @article{DBLP:journals/tip/WangL11,
    author = {Shu-Fan Wang and
    Shang-Hong Lai},
    title = {Compressibility-Aware Media Retargeting With Structure Preserving},
    journal = {IEEE Transactions on Image Processing},
    volume = {20},
    number = {3},
    year = {2011},
    pages = {855-865},
    ee = {http://dx.doi.org/10.1109/TIP.2010.2076293},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
30. Depth estimation from uncalibrated stereo images via hierarchical over-segmentation
  - L.-H. Chin, Y.-L. Chen, Y.-H. Li, J.-J. Hung, S.-H. Lai
  - International Conference on 3D Systems and Applications, Seoul, Korea, June 2011
31. Fast H.264 Encoding Based On Statistical Learning
  - C.-K. Chiang, W.-H. Pan, C. Hwang, S. Zhuang and S.-H. Lai
  - IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Vol. 21, Issue 9, pp.1304-1315, Sep. 2011. (bibtex)
  - @article{DBLP:journals/tcsv/ChiangPHZL11,
    author = {Chen-Kuo Chiang and
    Wei-Hau Pan and
    Chiuan Hwang and
    ShinShan Zhuang and
    Shang-Hong Lai},
    title = {Fast H.264 Encoding Based on Statistical Learning},
    journal = {IEEE Trans. Circuits Syst. Video Techn.},
    volume = {21},
    number = {9},
    year = {2011},
    pages = {1304-1315},
    ee = {http://dx.doi.org/10.1109/TCSVT.2011.2147250},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
32. Reconstructing 3D Face Model with Associated Expression Deformation from a Single Face Image via Constructing a Low-Dimensional Expression Deformation Manifold
  - S.-F. Wang and S.-H. Lai
  - IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 33, No. 10, pp.2115-2121, Oct. 2011 (bibtex)
  - @article{DBLP:journals/pami/WangL11,
    author = {Shu-Fan Wang and
    Shang-Hong Lai},
    title = {Reconstructing 3D Face Model with Associated Expression
    Deformation from a Single Face Image via Constructing a
    Low-Dimensional Expression Deformation Manifold},
    journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
    volume = {33},
    number = {10},
    year = {2011},
    pages = {2115-2121},
    ee = {http://doi.ieeecomputersociety.org/10.1109/TPAMI.2011.88},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
33. Spatio-temporally consistent novel view synthesis algorithm from video-plus-depth sequences for autostereoscopic displays
  - C.-M. Cheng, S.-J. Lin and S.-H. Lai
  - IEEE Transactions on Broadcasting, Vol. 57, No. 2, pp. 523-532, June 2011 (bibtex)
  - article{DBLP:journals/tbcas/SaighiBTMR11,
    author = {C.-M. Cheng and S.-J. Lin and S.-H. Lai},
    title = {Spatio-temporally consistent novel view synthesis algorithm from video-plus-depth sequences for autostereoscopic displays},
    journal = {IEEE Transactions on Broadcasting},
    volume = {57},
    number = {2},
    year = {2011},
    pages = {523-532},
    ee = {http://dx.doi.org/10.1109/TBC.2011.2139090},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
34. An optical flow based approach to robust face recognition under expression variations
  - C.-K. Hsieh, S.-H. Lai, and Y.-C. Chen
  - IEEE Transactions on Image Processing, Vol. 19, No. 1, pp. 233-240, Jan. 2010 (bibtex)
  - @article{DBLP:journals/tip/HsiehLC10,
    author = {Chao-Kuei Hsieh and
    Shang-Hong Lai and
    Yung-Chang Chen},
    title = {An Optical Flow-Based Approach to Robust Face Recognition
    Under Expression Variations},
    journal = {IEEE Transactions on Image Processing},
    volume = {19},
    number = {1},
    year = {2010},
    pages = {233-240},
    ee = {http://dx.doi.org/10.1109/TIP.2009.2031233},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
35. Binary Orientation Trees for Volume and Surface Reconstruction from Unoriented Point Clouds
  - Y.-L. Chen, B.-Y. Chen, S.-H. Lai and T. Nishita
  - Computer Graphics Forum (Proceedings of Pacific Graphics 2010), Vol.29, No. 7, pp. 2011-2019, Sep. 2010 (bibtex)
  - @article{DBLP:journals/cgf/ChenCLN10,
    author = {Yi-Ling Chen and
    Bing-Yu Chen and
    Shang-Hong Lai and
    Tomoyuki Nishita},
    title = {Binary Orientation Trees for Volume and Surface Reconstruction
    from Unoriented Point Clouds},
    journal = {Comput. Graph. Forum},
    volume = {29},
    number = {7},
    year = {2010},
    pages = {2011-2019},
    ee = {http://dx.doi.org/10.1111/j.1467-8659.2010.01787.x},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
36. Manifold-Based 3D Face Caricature Generation with Individualized Facial Feature Extraction
  - S.-F. Wang and S.-H. Lai
  - Computer Graphics Forum (Proceedings of Pacific Graphics 2010), Vol.29, No. 7, pp. 2161-2168, Sep. 2010. (bibtex)
  - @article{DBLP:journals/cgf/WangL10,
    author = {S. F. Wang and
    S. H. Lai},
    title = {Manifold-Based 3D Face Caricature Generation with Individualized
    Facial Feature Extraction},
    journal = {Comput. Graph. Forum},
    volume = {29},
    number = {7},
    year = {2010},
    pages = {2161-2168},
    ee = {http://dx.doi.org/10.1111/j.1467-8659.2010.01804.x},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
37. A consensus sampling technique for fast and robust model fitting
  - C.-M. Cheng and S.-H. Lai
  - Pattern Recognition, Vol. 42, No. 7, pp. 1318-1329, July 2009. (SCI, EI) (bibtex)
  - @article{DBLP:journals/pr/ChengL09,
    author = {Chia-Ming Cheng and
    Shang-Hong Lai},
    title = {A consensus sampling technique for fast and robust model
    fitting},
    journal = {Pattern Recognition},
    volume = {42},
    number = {7},
    year = {2009},
    pages = {1318-1329},
    ee = {http://dx.doi.org/10.1016/j.patcog.2009.01.007},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
38. Creating MPU Implicit Surfaces from Unoriented Point Sets with Orientation Inference
  - Y.-L. Chen and S.-H. Lai
  - Visual Computer: International Journal of Computer Graphics, Vol. 25, Issue 5-7, pp.391-399, Apr. 2009 (bibtex)
  - @article{DBLP:journals/vc/ChenL09,
    author = {Yi-Ling Chen and
    Shang-Hong Lai},
    title = {Creating MPU implicit surfaces from unoriented point sets
    with orientation inference},
    journal = {The Visual Computer},
    volume = {25},
    number = {5-7},
    year = {2009},
    pages = {391-399},
    ee = {http://dx.doi.org/10.1007/s00371-009-0354-0},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
39. Expression-invariant face recognition with constrained optical flow warping
  - C.-K. Hsieh, S.-H. Lai, and Y.-C. Chen
  - IEEE Trans. on Multimedia, Vol. 11, No. 4, pp. 600-610, June 2009. (SCI, EI) (bibtex)
  - @article{DBLP:journals/tmm/HsiehLC09,
    author = {Chao-Kuei Hsieh and
    Shang-Hong Lai and
    Yung-Chang Chen},
    title = {Expression-Invariant Face Recognition With Constrained Optical
    Flow Warping},
    journal = {IEEE Transactions on Multimedia},
    volume = {11},
    number = {4},
    year = {2009},
    pages = {600-610},
    ee = {http://dx.doi.org/10.1109/TMM.2009.2017606},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
40. Fast JND-Based Video Carving with GPU Acceleration for Real-Time Video Retargeting
  - C.-K. Chiang, S.-F. Wang, Y.-L. Chen and S.-H. Lai
  - IEEE Transactions on Circuits and Systems for Video Technology, Vol. 19, No. 11, pp. 1588-1597, Nov. 2009 (bibtex)
  - @article{DBLP:journals/tcsv/ChiangWCL09,
    author = {Chen-Kuo Chiang and Shu-Fan Wang and Yi-Ling Chen and Shang-Hong Lai},
    title = {Fast JND-Based Video Carving With GPU Acceleration for Real-Time Video Retargeting},
    journal = {IEEE Trans. Circuits Syst. Video Techn.},
    volume = {19},
    number = {11},
    year = {2009},
    pages = {1588-1597},
    ee = {http://dx.doi.org/10.1109/TCSVT.2009.2031462},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
41. Learning-based vertebra detection and iterative normalized-cut segmentation for spinal MRI
  - S.-H. Huang, Y.-H. Chu, S.-H. Lai, and C. L. Novak
  - IEEE Trans. Medical Imaging, Vol. 28, No. 10, pp. 1595-1605, Oct. 2009. (SCI, EI) (bibtex)
  - @article{DBLP:journals/tmi/HuangCLN09,
    author = {Szu-Hao Huang and
    Yi-Hong Chu and
    Shang-Hong Lai and
    Carol L. Novak},
    title = {Learning-Based Vertebra Detection and Iterative Normalized-Cut
    Segmentation for Spinal MRI},
    journal = {IEEE Trans. Med. Imaging},
    volume = {28},
    number = {10},
    year = {2009},
    pages = {1595-1605},
    ee = {http://dx.doi.org/10.1109/TMI.2009.2023362},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
42. Fast optimal motion estimation based on gradient-based adaptive multilevel successive elimination
  - S.-W. Liu, S.-D. Wei, and S.-H. Lai
  - IEEE Transactions Circuits and Systems for Video Technology, Vol. 18, No. 2, pp. 263-267, Feb. 2008. (SCI, EI) (bibtex)
  - @article{DBLP:journals/tcsv/LiuWL08,
    author = {Shao-Wei Liu and
    Shou-Der Wei and
    Shang-Hong Lai},
    title = {Fast Optimal Motion Estimation Based on Gradient-Based Adaptive
    Multilevel Successive Elimination},
    journal = {IEEE Trans. Circuits Syst. Video Techn.},
    volume = {18},
    number = {2},
    year = {2008},
    pages = {263-267},
    ee = {http://dx.doi.org/10.1109/TCSVT.2007.913973},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
43. Fast template matching based on normalized cross correlation with adaptive multilevel winner update
  - S.-D. Wei, and S.-H. Lai
  - IEEE Trans. on Image Processing, Vol. 17, No. 11, pp. 2227-2235, Nov. 2008. (SCI, EI) (bibtex)
  - @article{DBLP:journals/tip/WeiL08,
    author = {Shou-Der Wei and
    Shang-Hong Lai},
    title = {Fast Template Matching Based on Normalized Cross Correlation
    With Adaptive Multilevel Winner Update},
    journal = {IEEE Transactions on Image Processing},
    volume = {17},
    number = {11},
    year = {2008},
    pages = {2227-2235},
    ee = {http://dx.doi.org/10.1109/TIP.2008.2004615},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
44. Image-Based Three-Dimensional Model Reconstruction for Chinese Treasure - Jadeite Cabbage with Insects
  - C.-M. Cheng, S.-F. Wang, C.-H. Teng, and S.-H. Lai
  - Computer and Graphics (C&G), Vol. 32, No. 6, pp. 682-694, Dec. 2008 (bibtex)
  - @article{DBLP:journals/cg/ChengWTL08,
    author = {Chia-Ming Cheng and
    Shu-Fan Wang and
    Chin-Hung Teng and
    Shang-Hong Lai},
    title = {Image-based three-dimensional model reconstruction for Chinese
    treasure - Jadeite Cabbage with Insects},
    journal = {Computers {\&} Graphics},
    volume = {32},
    number = {6},
    year = {2008},
    pages = {682-694},
    ee = {http://dx.doi.org/10.1016/j.cag.2008.08.001},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
45. Reconstructing 3D Shape, Albedo and Illumination from a Single Face Image
  - S.-F. Wang and S.-H. Lai
  - Computer Graphics Forum (Proceedings of Pacific Graphics 2008), Vol.27, No. 7, pp. 1729-1736, Oct. 2008 (bibtex)
  - @article{DBLP:journals/cgf/WangL08,
    author = {Shu-Fan Wang and
    Shang-Hong Lai},
    title = {Reconstructing 3D Shape, Albedo and Illumination from a
    Single Face Image},
    journal = {Comput. Graph. Forum},
    volume = {27},
    number = {7},
    year = {2008},
    pages = {1729-1736},
    ee = {http://dx.doi.org/10.1111/j.1467-8659.2008.01317.x},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
46. Fast Multi-Reference Motion Estimation via Enhanced Downhill Simplex Search
  - C.-K. Chiang, H.-C. Fei and S.-H. Lai
  - Journal of VLSI Signal Processing Systems, vol. 46, Issue 2-3, March 2007, pp. 75-86. (bibtex)
  - @article{DBLP:journals/vlsisp/ChiangFL07,
    author = {Chen-Kuo Chiang and Hwai-Chung Fei and Shang-Hong Lai},
    title = {Fast Multi-reference Motion Estimation via Enhanced Downhill Simplex Search},
    journal = {VLSI Signal Processing},
    volume = {46},
    number = {2-3},
    year = {2007},
    pages = {75-86},
    ee = {http://dx.doi.org/10.1007/s11265-006-0033-6},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
47. Hybrid image matching combining Hausdorff distance with normalized gradient matching
  - C.-H. T. Yang, S.-H. Lai, and L.-W. Chang
  - Pattern Recognition, Vol. 40, No. 4, pp. 1173-1181, April 2007. (SCI, EI) (bibtex)
  - @article{DBLP:journals/pr/YangLC07,
    author = {Chyuan-Huei Thomas Yang and
    Shang-Hong Lai and
    Long-Wen Chang},
    title = {Hybrid image matching combining Hausdorff distance with
    normalized gradient matching},
    journal = {Pattern Recognition},
    volume = {40},
    number = {4},
    year = {2007},
    pages = {1173-1181},
    ee = {http://dx.doi.org/10.1016/j.patcog.2006.09.014},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
48. Robust fundamental matrix estimation with accurate outlier detection
  - J.-F. Huang, S.-H. Lai, and C.-M. Cheng
  - Journal of Information Science and Engineering, Vol. 23, No. 4, pp. 1213-1227, 2007. (SCI, EI) (bibtex)
  - @article{DBLP:journals/jise/HuangLC07,
    author = {Jing-Fu Huang and
    Shang-Hong Lai and
    Chia-Ming Cheng},
    title = {Robust Fundamental Matrix Estimation with Accurate Outlier
    Detection},
    journal = {J. Inf. Sci. Eng.},
    volume = {23},
    number = {4},
    year = {2007},
    pages = {1213-1225},
    ee = {http://www.iis.sinica.edu.tw/page/jise/2007/200707_16.html},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
49. Speech-Driven Mouth Animation Based on Support Vector Regression
  - C.-T. Liao, Y.-K. Wu, and S.-H. Lai
  - International Journal of Electronic Business Management, Vol. 5, No. 1, pp. 19-25, 2007
50. A robust real-time video stabilization algorithm
  - H.-C. Chang, S.-H. Lai, and K.-R. Lu
  - Journal of Visual Communication and Image Representation, Vol. 17, No. 3, pp. 659-673, June 2006. (SCI) (bibtex)
  - @article{DBLP:journals/jvcir/ChangLL06,
    author = {Hung-Chang Chang and
    Shang-Hong Lai and
    Kuang-Rong Lu},
    title = {A robust real-time video stabilization algorithm},
    journal = {J. Visual Communication and Image Representation},
    volume = {17},
    number = {3},
    year = {2006},
    pages = {659-673},
    ee = {http://dx.doi.org/10.1016/j.jvcir.2005.10.004},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
51. Improved adaboost-based image retrieval with relevance feedback via paired feature learning
  - S.-H. Huang, Q.-J. Wu, and S.-H. Lai
  - ACM Multimedia Systems Journal, Vol. 12, No. 1, pp. 14-26, August 2006. (SCI) (bibtex)
  - @article{DBLP:journals/mms/HuangWL06,
    author = {Szu-Hao Huang and
    Qi-Jiunn Wu and
    Shang-Hong Lai},
    title = {Improved AdaBoost-based image retrieval with relevance feedback
    via paired feature learning},
    journal = {Multimedia Syst.},
    volume = {12},
    number = {1},
    year = {2006},
    pages = {14-26},
    ee = {http://dx.doi.org/10.1007/s00530-006-0028-y},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
52. Robust and efficient image alignment based on relative gradient matching
  - S.-D. Wei and S.-H. Lai
  - IEEE Transactions on Image Processing, Vol. 15, No. 10, pp. 2936 – 2943, 2006. (SCI, EI) (bibtex)
  - @article{DBLP:journals/vlsisp/LiaoLL12,
    author = {S. D. Wei and
    S. H. Lai},
    title = {Robust and Efficient Image Alignment Based on Relative Gradient Matching},
    journal = {mage Processing, IEEE Transactions on},
    volume = {15},
    issue = {10},
    year = {2006},
    pages = {2936 - 2943},
    ee = {http://dx.doi.org/10.1109/TIP.2006.877500},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
53. Accurate optical flow computation under non-uniform brightness variations
  - C.-H. Teng, S.-H. Lai, Y. S. Chen, and W.-H. Hsu
  - Computer Vision and Image Understanding, Vol. 97, No. 3, pp. 315-346, 2005 (bibtex)
  - @article{DBLP:journals/cviu/TengLCH05,
    author = {Chin-Hung Teng and
    Shang-Hong Lai and
    Yung-Sheng Chen and
    Wen-Hsing Hsu},
    title = {Accurate optical flow computation under non-uniform brightness
    variations},
    journal = {Computer Vision and Image Understanding},
    volume = {97},
    number = {3},
    year = {2005},
    pages = {315-346},
    ee = {http://dx.doi.org/10.1016/j.cviu.2004.08.002},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
54. An adaptive window width/center adjustment system with online training capabilities for MR images
  - S.-H. Lai and M. Fang
  - Artificial Intelligence in Medicine, Vol. 33, No. 1, pp. 89-101, 2005 (bibtex)
  - @article{DBLP:journals/artmed/LaiF05,
    author = {Shang-Hong Lai and
    Ming Fang},
    title = {An adaptive window width/center adjustment system with online
    training capabilities for MR images},
    journal = {Artificial Intelligence in Medicine},
    volume = {33},
    number = {1},
    year = {2005},
    pages = {89-101},
    ee = {http://dx.doi.org/10.1016/j.artmed.2004.03.008},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
55. Computation of optical flow under non-uniform brightness variations
  - S.-H. Lai
  - Pattern Recognition Letters, Vol. 25, pp.885-892, 2004
56. A dual image approach for bias field correction in magnetic resonance imaging
  - S.-H. Lai and M. Fang
  - Magnetic Resonance Imaging, Vol. 21/2, pp. 121 - 125, 2003
57. A hybrid image alignment system for fast and precise pattern localization
  - S.-H. Lai and M. Fang
  - Real-Time Imaging, Vol. 8, Issue 1, pp. 23-33, Feb. 2002
58. A novel illumination compensation algorithm for industrial inspection
  - S.-H. Lai and M. Fang
  - Journal of Electronic Imaging, Vol. 10, No. 1, pp. 359-366, Jan. 2001
59. A hierarchical neural network algorithm for robust and automatic windowing of MR images
  - S.-H. Lai and M. Fang
  - Artificial Intelligence in Medicine, Vol. 19, Issue 2, pp. 97-119, June 2000
60. Robust image alignment under partial occlusion and spatially varying illumination change
  - S.-H. Lai
  - Computer Vision and Image Understanding, Vol. 78, pp. 84-98, 2000
61. A new variational shape-from-orientation approach to correcting intensity inhomogeneities in MR images
  - S.-H. Lai and M. Fang
  - Medical Image Analysis, Vol. 3, No. 4, pp. 409-424, 1999
62. A novel local PCA based method for detecting activation signals in MRI
  - S.-H. Lai and M. Fang
  - Magnetic Resonance Imaging, Vol. 17, No. 6, pp. 827-836, 1999
63. An accurate and fast pattern localization algorithm for automated visual inspection
  - S.-H. Lai and M. Fang
  - Real-Time Imaging, Vol. 5, Issue 1, pp. 3-14, Feb. 1999
64. Efficient hybrid search algorithm for visual reconstruction problems
  - S.-H. Lai and B.C. Vemuri
  - Image and Vision Computing, Vol. 17, Issue 1, pp.37-49, Jan. 1999
65. Generalized capacitance matrix theorems and algorithm for solving linear systems
  - S.-H. Lai and B.C. Vemuri
  - SIAM Journal on Scientific Computing, Vol. 19, No. 3, pp. 1024-1045, May 1998
66. A fast Gibbs sampler for synthesizing constrained fractals
  - B.C. Vemuri, C. Mandal and S.-H. Lai
  - IEEE Transactions on Visualization and Computer Graphics, Vol. 3, No. 4, pp. 337-351, 1997
67. Physically-based adaptive preconditioners for early vision
  - S.-H. Lai and B.C. Vemuri
  - IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No. 6, pp. 594-697, June 1997. (bibtex)
  - @ARTICLE{Lai97physically-basedadaptive,
    author = {S. H. Lai and B. C. Vemuri},
    title = {Physically-based Adaptive Preconditioning for Early Vision},
    journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    year = {1997},
    volume = {19},
    pages = {1--9}
    }
68. Sherman-Morrison-Woodbury formula-based algorithms for the surfaces smoothing problem
  - S.-H. Lai and B.C. Vemuri
  - Linear Algebra and Its Applications, Vol. 265, pp. 203-229, 1997 (bibtex)
  - @MISC{Lai_sherman-morrison-woodburyformula-based,
    author = {Shang-hong Lai and B. C. Vemuri},
    title = {Sherman-Morrison-Woodbury Formula-based Algorithms for the Surface Smoothing Problem},
    year = {}
    }
69. Fast algorithms for fitting multiresolution hybrid shape models to brain MRI
  - B.C. Vemuri, Y. Guo, S.-H. Lai and C.M. Leonard
  - Medical Image Analysis, Vol. 1, No. 4, pp.343-362, 1997 (bibtex)
  - @MISC{Vemuri96fastalgorithms,
    author = {B. C. Vemuri and Y. Guo and S. H. Lai and C. M. Leonard},
    title = {Fast Algorithms for Fitting Multiresolution Hybrid Shape Models to Brain MRI},
    year = {1996}
    }
70. Robust and efficient computation of optical flow
  - S.-H. Lai and B.C. Vemuri
  - International Journal of Computer Vision, Vol. 29, No. 2, pp. 87-105, 1998 (bibtex)
  - @MISC{Lai95robustand,
    author = {S.H. Lai and B.C. Vermuri},
    title = {Robust and Efficient Computation of Optical Flow},
    year = {1995}
    }
71. A generalized depth estimation algorithm with a single image
  - S.-H. Lai, C.W. Fu and S. Chang
  - IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 14, No. 4, pp. 405-411, April, 1992
72. Motion parameter estimation in three-dimensional dynamic scenes: a Hadamard transform approach
  - C.W. Fu, S.-H. Lai and S. Chang
  - Journal of Information Science and Engineering, Vol. 8, No. 3, pp. 321-342, Sep. 1992. (bibtex)
  - @article{DBLP:journals/jise/FuLC92,
    author = {Chang-Wu Fu and
    Shang-Hong Lai and
    Shyang Chang},
    title = {Motion Parameter Estimation in Three-Dimensional Dynamic
    Scenes: a Hadamard Transform Approach},
    journal = {J. Inf. Sci. Eng.},
    volume = {8},
    number = {3},
    year = {1992},
    pages = {321-341},
    ee = {http://www.iis.sinica.edu.tw/page/jise/1992/199209_01.html},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
73. Estimation of three-dimensional motion parameters via Hadamard transform
  - S.-H. Lai and S. Chang
  - Pattern Recognition Letters, Vol.8, Issue 5, pp.341–345, Dec. 1988
Local Journal Papers
1. Person Identification under Multi-View Video Surveillance Environments
  - C.-T. Liao, S.-F. Wang, T.-Y. Lin, S.-H. Lai, and W.-H. Wang
  - Image and Recognition, Vol. 15 No. 2, 2009. (invited)
2. Combining foreground extraction and human detection for video surveillance
  - H.-C. Zeng S. Huang and S.-H. Lai
  - Image and Recognition, Vol. 13, No. 1, 2007. (invited)
3. Recent advances in automatic PCB inspection
  - C.-C. Kuo, S.-H. Lai, S. Y.-C. Yeh, D.-K. Liu, T. Ku
  - Image and Recognition, Vol. 10, No. 2, 2004. (invited)
4. Video shot segmentation: a survey
  - S.-H. Lai and W.-K. Li
  - Image and Recognition, Vol. 8, No. 1, 2002. (invited)
5. 3D face model reconstruction from an image sequence
  - C.-M. Cheng and S.-H. Lai
  - Image and Recognition, Vol. 7, No. 1, 2001 (invited)
Conference Papers
1. Disentangled Representation with Dual-stage Feature Learning for Face Anti-spoofing
  - Yu-Chun Wang, Chien-Yi Wang, Shang-Hong Lai
  - IEEE Workshop on Applications of Computer Vision (WACV), Waikoloa, Hawaii, USA, Jan. 2022
2. Multi-Scale Patch-Based Representation Learning for Image Anomaly Detection and Segmentation
  - Chin-Chia Tsai, Tsung-Hsuan Wu, Shang-Hong Lai
  - IEEE Workshop on Applications of Computer Vision (WACV), Waikoloa, Hawaii, USA, Jan. 2022
3. Attention-Based Deep Metric Learning for Near-Duplicate Video Retrieval
  - Kuan-Hsun Wang, Chia-Chun Cheng, Yi-Ling Chen, Yale Song, Shang-Hong Lai
  - International Conference on Pattern Recognition
4. Confidence-Aware anomaly detection in human actions
  - Tsung Hsuan Wu, Chun Lung Yang, Li Ling Chiu, Ting Wei Wang, Gueter Josmy Faure, Shang-Hong Lai
  - Asian Conference on Pattern Recognition (ACPR), Nov. 2021
5. High-Accuracy RGB-D Face Recognition via Segmentation-Aware Face Depth Estimation and Mask-Guided Attention Network
  - Meng-Tzu Chiu, Hsun-Ying Cheng, Chien-Yi Wang, Shang-Hong Lai
  - IEEE conference on Automatic Face and Gesture Recognition (FG), Dec. 2021
6. Moving-Object-Aware Anomaly Detection in Surveillance Videos
  - Chun-Lung Yang, Tsung-Hsuan Wu, Shang-Hong Lai
  - IEEE Int'l Conf on Advanced Video and Signal-based Surveillance (AVSS), Nov. 2021
7. Stylized-Colorization for Line Arts. International Conference on Pattern Recognition.
  - Tzu-Ting Fang, Minh Duc Vo, Akihiro Sugimoto, Shang-Hong Lai
  - MOST 108-2634-F-007-002.
8. 3D Object Detection from Consecutive Monocular Images
  - Chia-Chun Cheng, Shang-Hong Lai
  - Proceedings of the Asian Conference on Computer Vision (ACCV), 2020
9. ByeGlassesGAN: Identity Preserving Eyeglasses Removal for Face Images
  - Yu-Hui Lee, Shang-Hong Lai
  - European Conference on Computer Vision (ECCV) (29) 2020: 243-258
10. Learning to Match 2D Images and 3D LiDAR Point Clouds for Outdoor Augmented Reality
  - Weiquan Liu, Baiqi Lai, Cheng Wang, Xuesheng Bian, Wentao Yang, Yan Xia, Xiuhong Lin, Shang-Hong Lai
  - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW)
11. Multimodal Structure-Consistent Image-to-Image Translation
  - Che-Tsung Lin, Yen-Yi Wu, Po-Hao Hsu, & Shang-Hong Lai
  - Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence (AAAI), Feb 2020.
12. Unified Representation Learning for Cross Model Compatibility
  - Chien-Yi Wang, Ya-Liang Chang, Shang-Ta Yang, Dong Chen, Shang-Hong Lai
  - The British Machine Vision Conference (BMVC), 2020
13. Audio Tempo Estimation Method Improved by Rhythm Pattern and Data Augmentation
  - Fu-Hai Frank Wu, Shang-Hong Lai
  - 2019 6th International Conference on Control, Decision and Information Technologies (CoDIT) 2019: 779-784
14. Automatic Generation of Photorealistic Training Data for Detection of Industrial Components
  - Yu-Hui Lee, Chu-Chun Chuang, Shang-Hong Lai, Zih-Jian Jhang
  - IEEE International Conference on Image Processing (ICIP), pp. 2751-2755, Sep. 2019
15. DeepRoom: 3D Room Layout and Camera Pose Estimation from a Single Image
  - Hung Jin Lin and Shang-Hong Lai
  - Asian Conference on Pattern Recognition, Auckland, New Zealand, Nov. 2019
16. Ground Camera Images and UAV 3D Model Registration for Outdoor Augmented Reality
  - W. Liu, C. Wang, Y. Zang, SH Lai, D. Weng, X. Sian, X. Lin, X. Shen, J. Li
  - 2019 IEEE Conference on Virtual Reality and 3D User Interfaces (VR)
17. Group Activity Recognition via Computing Human Pose Motion History and Collective Map from Video
  - Hsing-Yu Chen and Shang-Hong Lai
  - Asian Conference on Pattern Recognition, Auckland, New Zealand, Nov. 2019
18. i-Siam: Improving Siamese Tracker with Distractors Suppression and Long-Term Strategies
  - Wei Ren Tan and Shang-Hong Lai
  - IEEE International Conference on Computer Vision (ICCV) Workshops, Oct. 2019
19. Object Detection in Curved Space for 360-Degree Camera
  - Kuan-Hsun Wang and Shang-Hong Lai
  - IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), Brighton, UK, May 2019
20. A Compact Deep Learning Model for Robust Facial Expression Recognition
  - Chieh-Ming Kuo, Shang-Hong Lai and Michel Sarkis
  - CVPR Workshop on Analysis and Modeling of Faces and Gestures, Salk Lake City, Utah, USA, June 2018
21. AugGAN: Cross Domain Adaptation with GAN-based Data Augmentation
  - Sheng-Wei Huang*, Che-Tsung Lin*, Shu-Ping Chen, Yen-Yi Wu, Po-Hao Hsu, & Shang-Hong Lai
  - European Conference on Computer Vision (ECCV), Sep 2018. *= Equal Contribution
22. Emotion-Preserving Representation Learning via Generative Adversarial Network for Multi-view Facial Expression Recognition
  - Ying-Hsiu Lai and Shang-Hong Lai
  - The 13th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2018) , Xi’an, China, May 15-19, 2018
23. Human Action Recognition Based on Temporal Pose CNN and Multi-dimensional Fusion
  - Yi Huang, Shang-Hong Lai, Shao-Heng Tai
  - European Conference on Computer Vision(ECCV) Workshops, Munich, Germany, Sep. 2018
24. Indoor Scene Layout Estimation from a Single Image
  - Hung-Jin Lin, Sheng-Wei Huang, Shang-Hong Lai, Chen-Kuo Chiang
  - International Conference on Pattern Recognition (ICPR), Beijing, China, Aug. 2018
25. Non-native Language Reading Support with Display of Machine Translation Based on Eye-Tracking and Sentence-Level Mapping
  - Tien-Yu Ho, Hao-Chuan Wang and Shong-Hong Lai
  - Chinese CHI, Montréal, Canada, April 2018
26. SegmentedFusion: 3D Human Body Reconstruction Using Stitched Bounding Boxes
  - Shih-Hsuan Yao, Diego Thomas, Akihiro Sugimoto, Shang-Hong Lai, Rin-ichiro Taniguchi
  - International Conference on 3D Vision (3DV), Verona, Italy, Sept. 2018
27. A Deep Learning Approach to Appearance-Based Gaze Estimation under Head Pose Variations
  - Hsin-Pei Sun, Cheng-Hsun Yang and Shang-Hong Lai
  - Asian Conference on Pattern Recognition, Nanjing, China, November, 2017
28. A deep learning approach towards pore extraction for high-resolution fingerprint recognition
  - H.-R. Su, K.-Y. Chen, W. J. Wong, S.-H. Lai
  - International Conference on Acoustics, Speech, and Signal Processing (ICASSP), New Orleans, USA, March, 2017
29. Deep Neural Networks for Accurate Iris Recognition
  - Yuzheng Xu,Tzu-Chan Chuang, Shang-Hong Lai
  - Asian Conference on Pattern Recognition, Nanjing, China, November, 2017
30. Edge-Preserving Disparity Map Estimation from Stereo Videos for Bokeh Synthesis
  - W.-L. Lan, S.-H. Yao, and S.-H. Lai
  - IEEE International Conf. on Multimedia and Expo. (ICME), Hong Kong, July, 2017
31. Fast Vehicle Detector for Autonomous Driving
  - Che-Tsung Lin, Patrisia Sherryl Santoso, Shu-Ping Chen, Hung-Jin Lin and Shang-Hong Lai
  - International Conference of Computer Vision Workshop, Oct, 2017
32. General Deep Image Completion with Lightweight Conditional Generative Adversarial Networks
  - Ching-Wei Tseng, Hung Jin Lin, Shang-Hong Lai
  - British Machine Vision Conference, London, September, 2017
33. Gesture Recognition from Depth Images with Hierarchical Hand Parsing
  - M. Lin and S.-H. Lai
  - Asia-Pacific Workshop on Mixed and Augmented Reality, Beijing, China, July 2017
34. Hierarchical structured dictionary learning for image categorization
  - T.-C. Chuang, C.-K. Chiang, S.-H. Lai
  - International Conference on Acoustics, Speech, and Signal Processing (ICASSP), New Orleans, USA, March, 2017
35. Accurate and robust face recognition from RGB-D images with a deep learning approach
  - Y. Lee, J. Chen, C. W. Tseng and S.-H. Lai
  - British Machine Vision Conference (BMVC), York, UK, Sep. 2016
36. Depth image super-resolution via multi-frame registration and deep learning
  - C.-W. Tseng, H.-R. Su, and S.-H. Lai
  - APSIPA Annual Summit and Conference, Jeju, Korea, Dec. 2016
37. Driver drowsiness detection via a hierarchical temporal deep belief network
  - C.-H. Weng, Y.-H. Lai, S.-H. Lai
  - ACCV Workshop on Drowsy Driver Detection from Video, Taipei, Taiwan, Nov. 2016
38. Lighting Estimation from a Single Image Containing Multiple Planes
  - P.-C. Kuo and S.-H. Lai
  - ACM Multimedia Systems Conference (MMSys), Klagenfurt, Austria, May, 2016
39. Video stabilization with distortion correction for wide-angle lens dashcam
  - H.Y. Huang, S.-H. Yeh, C.-T. Lin, and S.-H. Lai
  - APSIPA Annual Summit and Conference, Jeju, Korea, Dec. 2016
40. 3D Hand Skeleton Model Estimation from a Depth Image
  - Chin-Yun Fan, Meng-Hsuan Lin, Te-Feng Su, Shang-Hong Lai, Chih-Hsiang Yu
  - International Association for Pattern Recognition on Machine Vision Applications (IAPR MVA2015), Tokyo, Japan, May 2015
41. Correcting Radial and Perspective Distortion by Using Face Shape Information
  - Tung-Ying Lee, Tzu-Shan Chang, and Shang-Hong Lai
  - 11Th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2015) , Ljubljana, Slovenia, May 4-8, 2015
42. Hierarchical Interpolation-Based Disocclusion Region Recovery for Two-View to N-View Conversion System
  - W.-T. Lin, C.-T. Yeh, and S.-H. Lai,
  - Pacific-Rim Conference on Multimedia, Gwangju, Korea, Sep. 2015
43. Non-rigid Registration of Images with Geometric and Photometric Deformation by Using Local Affine Fourier-Moment Matching
  - Hong-Ren Su, Shang-Hong Lai
  - Computer Vision and Pattern Recognition(CVPR), Boston, Massachusetts, USA, June 2015
44. Novel Facial Expression Recognition by Combining Action Unit Detection with Sparse Representation Classification
  - Te-Feng Su, Ching-Hua Weng, Shang-Hong Lai
  - COMPSAC Symposium on Human-Machine and Aware Computing, Taichung, Taiwan, July 1-5, 2015.
45. Simultaneous Stereo Rectification and Distortion Correction with Application to DoF Synthesis
  - C.-T. Yeh, T.-Y. Ho, S.-H. Huang, and S.-H Lai
  - Pacific Conference on Computer Graphics and Applications (PG), Beijing, Oct. 2015
46. Sparse Representation Based Approach for RGB-D Hand Gesture Recognition
  - Te-Feng Su, Chin-Yun Fan, Meng-Hsuan Lin, and Shang-Hong Lai,
  - Pacific-Rim Conference on Multimedia, Gwangju, Korea, Sep. 2015
47. Using Line Consistency to Estimate 3D Indoor Manhattan Scene Layout from a Single Image
  - Hsing-Chun Chang, Szu-Hao Huang, and Shang-Hong Lai,
  - International Conference on Image Processing, Quebec City, Canada, Sep. 2015
48. 3D Liver Vessel Reconstruction from CT Images
  - Xing-Chen Pan , Hong-Ren Su, Shang-Hong Lai, Kai-Che Liu , Hurng-Sheng Wu
  - 3DV : Dynamic Shape Measurement and Analysis workshop, Tokyo, Japan, Dec.2014
49. 3D object detection and pose estimation from depth image for robotic bin picking
  - Hao-Yuan Kuo, Hong-Ren Su, Shang-Hong Lai, Chin-Chia Wu
  - IEEE International Conference on Automation Science and Engineering(IEEE CASE),Taipei,Taiwan,Aug.2014
50. 3D Reconstruction with Automatic Foreground Segmentation from Multi-View images Acquired from a Mobile Device
  - Ping-Cheng Kuo, Chao-An Chen, Hsing-Chun Chang, Te-Feng Su, Shang-Hong Lai
  - 3rd International Workshop on Intelligent Mobile and Egocentric Vision (IMEV), Singapore, Nov.2014
51. Fast 3D Object Alignment from Depth Image with 3D Fourier Moment Matching on GPU
  - Hong-Ren Su, Hao-Yuan Kuo, Shang-Hong Lai, Chin-Chia Wu
  - International Conference on 3D Vision(3DV), Tokyo, Japan, Dec.2014
52. Integrated Vehicle and Lane Detection with Distance Estimation
  - Yu-Chun Chen, Te-Feng Su, Shang-Hong Lai
  - 3rd International Workshop on Intelligent Mobile and Egocentric Vision (IMEV), Singapore, Nov.2014
53. ONLINE FACIAL EXPRESSION RECOGNITION BASED ON COMBINING TEXTURE AND GEOMETRIC INFORMATION
  - Ching-Hua Weng, Shang-Hong Lai, Michel Sarkis
  - IEEE International Conference on Image Processing (ICIP), Paris, France, Oct.2014
54. EFFICIENT VEHICLE DETECTION WITH ADAPTIVE SCAN BASED ON PERSPECTIVE GEOMETRY
  - Yu-Chun Chen, Te-Feng Su, and Shang-Hong Lai
  - IEEE International Conference on Image Processing (ICIP), Melbourne, Australia, Sep.2013
55. Fast Image Alignment with Fourier Moment Matching on GPU
  - H.-R. Su, H.-Y. Kuo, S.-H. Lai and C.-C. Wu
  - APSIPA ASC, Kaohsiung, Taiwan, Nov. 2013
56. Human Segmentation from Video by Combining Random Walks with Human Shape Prior Adaption
  - Y.-T. Lee, T.-F. Su, H.-R. Su, S.-H. Lai, T.-C. Lee and M.-Y. Shih
  - APSIPA ASC, Kaohsiung, Taiwan, Nov. 2013
57. Multi-Attribute Sparse Representation with Group Constraints for Face Recognition under Different Variations
  - C.K. Chiang, T. F. Su, C. Yen and S. H. Lai
  - 10th IEEE International Conference on Automatic Face and Gesture Recognition (FG2013) April 22-26, 2013, Shanghai, China
58. Multi-Attributed Dictionary Learning for Sparse Coding
  - Chen-Kuo Chiang, Te-Feng Su, Yen Chih and Shang-Hong Lai
  - International Conference on Computer Vision (ICCV), Sydney, Australia, Dec, 2013
59. Negative-Voting and Class Ranking Based on Local Discriminant Embedding for Image Retrieval
  - Mei-Huei Lin, Chen-Kuo Chiang and Shang-Hong Lai
  - APSIPA ASC, Kaohsiung, Taiwan, Nov. 2013
60. Novel 3D Video Conversion from Down-Sampled Stereo Video
  - W.-T. Lin and S.-H. Lai
  - APSIPA ASC, Kaohsiung, Taiwan, Nov. 2013
61. Reconstruction of 3-D vertebra and spinal cord models from CT and STIR-MRI images
  - C. Yen, H.-R. Su and S.-H. Lai
  - Asian Conf. on Pattern Recognition, Okinawa, Japan, Nov. 2013.
62. ROLLING SHUTTER CORRECTION FOR VIDEO WITH LARGE DEPTH OF FIELD
  - Yen-Hao Chiao, Tung-Ying Lee, Shang-Hong Lai
  - International Conference on Image Processing (ICIP), Melbourne, Australia, Sep. 2013.
63. Single Image Super-Resolution Based on Local Self-Similarity
  - W.-T. Lin and S.-H. Lai
  - Asian Conf. on Pattern Recognition, Okinawa, Japan, Nov. 2013.
64. 3D Liver Segmentation and Model Reconstruction from CT Images
  - Y. Y. Cheng, H. M. Chang, H. R. Su, S. H. Lai, K. C. Liu and C. H. Lin.
  - iCBEB, 654-657, 2012.
65. 3D Spinal Cord and Nerves Segmentation from STIR-MRI.
  - C. Yen, H.R. Su, S.H. Lai, K.C. Liu, R.R. Lee
  - International Computer Symposium , 2012.(will be published by Springer-Verlag in series of Smart Innovation, Systems and Technologies)
66. Global Optimization For Spatio-Temporally Consistent View Synthesis
  - H.-A. Hsu, C.-K. Chiang and S.-H. Lai
  - APSIPA ASC, Hollywood, California
67. Learning expression kernels for facial expression intensity estimation
  - C.-T. Liao, H.-J. Chuang, S.-H. Lai
  - accept to present at IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, March 2012 (bibtex)
  - @inproceedings{DBLP:conf/icassp/LiaoCL12,
    author = {Chia-Te Liao and
    Hui-Ju Chuang and
    Shang-Hong Lai},
    title = {Learning expression kernels for facial expression intensity
    estimation},
    booktitle = {ICASSP},
    year = {2012},
    pages = {2217-2220},
    ee = {http://dx.doi.org/10.1109/ICASSP.2012.6288354},
    crossref = {DBLP:conf/icassp/2012},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
    @proceedings{DBLP:conf/icassp/2012,
    title = {2012 IEEE International Conference on Acoustics, Speech
    and Signal Processing, ICASSP 2012, Kyoto, Japan, March
    25-30, 2012},
    booktitle = {ICASSP},
    publisher = {IEEE},
    year = {2012},
    isbn = {978-1-4673-0046-9},
    ee = {http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6268628},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
68. Novel Multi-View Synthesis from a Stereo Image Pair for 3D Display on Mobile Phone
  - C. H. Wei, C. K. Chiang, Y. W. Sun, M. H. Lin, S. H. Lai
  - 2012 ACCV-IMV Workshop
69. Parallelized Background Substitution System on a Multi-core Embedded Platform
  - Yutzu Lee, Chen-Kuo Chiang, Te-Feng Su, Yu-Wei Sun, Chi-Bang Kuan, Shang-Hong Lai
  - 2012 41st International Conference on Parallel Processing Workshops, Pittsburgh(ICPP Workshops), PA, USA, September 10-13, 2012, page 530-537 (bibtex)
  - @inproceedings{DBLP:conf/icppw/LeeCSSKL12,
    author = {Yutzu Lee and
    Chen-Kuo Chiang and
    Te-Feng Su and
    Yu-Wei Sun and
    Chi-Bang Kuan and
    Shang-Hong Lai},
    title = {Parallelized Background Substitution System on a Multi-core
    Embedded Platform},
    booktitle = {ICPP Workshops},
    year = {2012},
    pages = {530-537},
    ee = {http://doi.ieeecomputersociety.org/10.1109/ICPPW.2012.72},
    crossref = {DBLP:conf/icppw/2012},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
    @proceedings{DBLP:conf/icppw/2012,
    title = {2012 41st International Conference on Parallel Processing
    Workshops, Pittsburgh, PA, USA, September 10-13, 2012},
    booktitle = {ICPP Workshops},
    publisher = {IEEE Computer Society},
    year = {2012},
    isbn = {978-1-4673-2509-7},
    ee = {http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6336539},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
70. Parallelized random walk algorithm for background substitution on a multi-core embedded platform
  - Y. Lee, C.-K. Chiang, Y.-W. Sun, T.-F. Su, S.-H. Lai
  - 2012 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2012, Kyoto, Japan, March 25-30, 2012, page 1621-1624 (bibtex)
  - @inproceedings{DBLP:conf/icassp/LeeCSSL12,
    author = {Yutzu Lee and
    Chen-Kuo Chiang and
    Yu-Wei Sun and
    Te-Feng Su and
    Shang-Hong Lai},
    title = {Parallelized Random Walk algorithm for background substitution
    on a multi-core embedded platform},
    booktitle = {ICASSP},
    year = {2012},
    pages = {1621-1624},
    ee = {http://dx.doi.org/10.1109/ICASSP.2012.6288205},
    crossref = {DBLP:conf/icassp/2012},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
    @proceedings{DBLP:conf/icassp/2012,
    title = {2012 IEEE International Conference on Acoustics, Speech
    and Signal Processing, ICASSP 2012, Kyoto, Japan, March
    25-30, 2012},
    booktitle = {ICASSP},
    publisher = {IEEE},
    year = {2012},
    isbn = {978-1-4673-0046-9},
    ee = {http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6268628},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
71. Real-Time Correction of Wide-Angle Lens Distortion for Images with GPU Computing
  - Tung-Ying Lee, Chen-Hao Wei, Shang-Hong Lai, and Ruen-Rone Lee
  - In Proceedings of IEEE Asia Pacific Conference on Circuits and Systems (APCCAS 2012), Dec. 2012.
72. Search Space Reduction in Pedestrian Detection for Driver Assistance System Based on Projective Geometry
  - K. Dimza, T.F. Su, S.H. Lai.
  - International Computer Symposium , 2012.(will be published by Springer-Verlag in series of Smart Innovation, Systems and Technologies)
73. Single-Shot Person Re-identification Based on Improved Random-Walk Pedestrian Segmentation
  - Y.-C. Chang, C.-K. Chiang and S.-H. Lai
  - IEEE International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)
74. Texture Feature Analysis of Ultrasonic Images with Wryneck
  - Hsiao-Mei Chang, Ya-Yun Cheng, Hong-Ren Su, Shang-Hong Lai, Chu-Hsu Lin, and Hung-Chih Hsu
  - In Internal Conference on Biomedical Engineering and Biotechnology 2012 (iCBEB 2012) (bibtex)
  - @inproceedings{DBLP:conf/icassp/LeeCSSL12,
    author = {H.M. Chang and Y. Y. Cheng and H.R. Su and S.H. Lai and C.H. Lin and H.C. Hsu },
    title = {Texture Feature Analysis of Ultrasonic Images with Wryneck },
    booktitle = { iCBEB },
    year = {2012},
    pages = {909 - 912 },
    ee = {http://dx.doi.org/ 10.1109/iCBEB.2012.396},
    crossref = {DBLP:conf/ iCBEB /2012},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
    @proceedings{DBLP:conf/icassp/2012,
    title = { Biomedical Engineering and Biotechnology (iCBEB), 2012 International Conference on 28-30 May 2012 },
    booktitle = {ICASSP},
    publisher = {IEEE},
    year = {2012},
    isbn = 978-1-4577-1987-5 },
    ee = { http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6245269 },
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
75. Accurate depth map estimation from video via MRF optimization
  - S.-P. Tseng and S.-H. Lai
  - Proc.Visual Communication and Image Processing Conference (VCIP), Tainan, Taiwan, Nov. 2011
76. Bipartite Polar Classification for Surface Reconstruction
  - Y.-L. Chen, T.-Y. Lee, B.-Y. Chen, S.-H. Lai
  - Pacific Graphics (PG), Kaohsiung, Taiwan, Sep. 2011
77. Blind Image Deblurring with Modified Richardson-Lucy Deconvolution for Ringing Artifact Suppression
  - Hao-Liang Yang, Yen-Hao Chiao, Po-Hao Huang, Shang-Hong Lai
  - 5th Pacific Rim Symposium, PSIVT 2011, Gwangju, South Korea, November 20-23, 2011, Proceedings, Part II (bibtex)
  - @inproceedings{Yang:2011:BID:2178036.2178058,
    author = {Yang, Hao-Liang and Chiao, Yen-Hao and Huang, Po-Hao and Lai, Shang-Hong},
    title = {Blind image deblurring with modified richardson-lucy deconvolution for ringing artifact suppression},
    booktitle = {Proceedings of the 5th Pacific Rim conference on Advances in Image and Video Technology - Volume Part II},
    series = {PSIVT'11},
    year = {2012},
    isbn = {978-3-642-25345-4},
    location = {Gwangju, South Korea},
    pages = {240--251},
    numpages = {12},
    url = {http://dx.doi.org/10.1007/978-3-642-25346-1_22},
    doi = {10.1007/978-3-642-25346-1_22},
    acmid = {2178058},
    publisher = {Springer-Verlag},
    address = {Berlin, Heidelberg},
    }
78. CT-MR image registration in 3D K-Space based on Fourier moment matching
  - H.-R. Su and S.-H. Lai
  - Proc. Pacific-Rim Symposium on Image and Video Technology (PSIVT), Vol. 2, pp. 299-310, 2011
79. Depth map estimation from multi-view images and videos for 3DTV
  - L.-H. Chin, S.-P. Tseng and S.-H. Lai
  - International Display Manufacturing Conference (IDMC), Taipei, April 2011
80. Detecting Moving Objects from Dynamic Background with Shadow Removal
  - S.-C. Wang, T.-F. Su, and S.-H. Lai
  - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, May 22-27, 2011 (Oral)
81. From co-saliency to co-segmentation: an efficient and fully unsupervised energy minimization model
  - K.-Y. Chang, T.-L. Liu, and S.-H. Lai
  - IEEE Conference on Computer Vision & Pattern Recognition (CVPR), Colorado Spring, Colorado, USA, June 2011
82. Fusing Generic Objectness and Visual Saliency for Salient Object Detection
  - K.-Y. Chang, T.-L. Liu
  - Proc. International Conference on Computer Vision (ICCV), Bercelona, Spain, Nov. 2011
83. Learning Component-Level Sparse Representation Using Histogram Information for Image Classification
  - C.-K. Chiang, C.-H. Duan, S.-H. Lai and S.-F. Chang
  - International Conference on Computer Vision (ICCV), Barcelona, Spain, 2011 (bibtex) (pdf)
  - @inproceedings{DBLP:conf/iccv/ChiangDLC11,
    author = {Chen-Kuo Chiang and
    Chih-Hsueh Duan and
    Shang-Hong Lai and
    Shih-Fu Chang},
    title = {Learning component-level sparse representation using histogram
    information for image classification},
    booktitle = {ICCV},
    year = {2011},
    pages = {1519-1526},
    ee = {http://dx.doi.org/10.1109/ICCV.2011.6126410},
    crossref = {DBLP:conf/iccv/2011},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
84. Parallelization of a Bokeh application on embedded multicore DSP systems
  - C.-B. Kuan, S.-C. Wang, W.-L. Shih, K.-H. Tsai
  - Proc. IEEE Symposium on Embedded Systems for Real-Time Multimedia (ESTImedia), pp. 93-101, Taipei, Oct. 2011
85. Parallelized Face Based RMS System on a Multi-core Embedded Computing Platform
  - T.-F. Su, J.-J. Li, C.-H. Duan, S.-F. Wang, and S.-H. Lai
  - ICPP Workshop on Embedded Multicore Systems(ICPP_EMS), Taipei, Taiwan, september, 2011
86. Pedestrian image segmentation via shape-prior constrained random walks
  - K.-C. Li, H.-R. Su, and S.-H. Lai
  - Proc. Pacific-Rim Symposium on Image and Video Technology (PSIVT), Vol. 2, pp. 215-226, 2011
87. People Localization in a Camera Network Combining Background Subtraction and Scene-Aware Human Detection
  - T.-Y. Lee, T.-Y. Lin, S.-H. Huang, S.-H. Lai, S.-C. Hung
  - International Multi-Media Modeling Conference (MMM), 2011. (bibtex)
  - @inproceedings{DBLP:conf/mmm/LeeLHLH11,
    author = {Tung-Ying Lee and
    Tsung-Yu Lin and
    Szu-Hao Huang and
    Shang-Hong Lai and
    Shang-Chih Hung},
    title = {People Localization in a Camera Network Combining Background
    Subtraction and Scene-Aware Human Detection},
    booktitle = {MMM (1)},
    year = {2011},
    pages = {151-160},
    ee = {http://dx.doi.org/10.1007/978-3-642-17832-0_15},
    crossref = {DBLP:conf/mmm/2011-1},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
    
    @proceedings{DBLP:conf/mmm/2011-1,
    editor = {Kuo-Tien Lee and
    Wen-Hsiang Tsai and
    Hong-Yuan Mark Liao and
    Tsuhan Chen and
    Jun-Wei Hsieh and
    Chien-Cheng Tseng},
    title = {Advances in Multimedia Modeling - 17th International Multimedia
    Modeling Conference, MMM 2011, Taipei, Taiwan, January 5-7,
    2011, Proceedings, Part I},
    booktitle = {MMM (1)},
    publisher = {Springer},
    series = {Lecture Notes in Computer Science},
    volume = {6523},
    year = {2011},
    isbn = {978-3-642-17831-3},
    ee = {http://dx.doi.org/10.1007/978-3-642-17832-0},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
88. Recovering depth map from video with moving objects
  - H.-W. Chen and S.-H. Lai
  - Proc. Pacific-Rim Symposium on Image and Video Technology (PSIVT), Vol. 2, pp. 335-346, 2011
89. Robust 3D object pose estimation from a single 2D image
  - C.-M. Cheng, H.-W. Chen, S.-H. Lai, and Y.-H. Tsai
  - Proc. Visual Communication and Image Processing Conference (VCIP), Tainan, Taiwan, Nov. 2011
90. Support of software framework for embedded multi-core systems with Android environments
  - Y.-H.Chang, C.-B. Kuan, C.-Y. Lin, T.-F. Su, C.-T. Chen, J.-S. Jang
  - Proc. IEEE Symposium on Embedded Systems for Real-Time Multimedia (ESTImedia), pp. 2-8, Taipei, Oct. 2011
91. Wide Angle Distortion Correction by Hough Transform and Gradient Estimation
  - T.-Y. Lee, T.-S. Chang, and S.-H. Lai
  - Proc. Visual Communication and Image Processing Conference (VCIP), Tainan, Taiwan, Nov. 2011
92. A Learning-based system for generating exaggerative caricature from face images with expression
  - T.-T. Yang and S.-H. Lai
  - IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Dallas, Texas, USA, March 14-19, 2010.
93. A novel structure-from-motion strategy for refining depth map estimation and multi-view synthesis in 3DTV
  - C.-M. Cheng, L.-H. Chin, X.-A. Hsu and S.-H. Lai
  - Proc. IEEE Conf. Multimedia and Expo. (ICME), Singapore, June 2010.
94. Accurate Facial Feature Localization on Expressional Face Images Based on a Graphical Model Approach
  - C.-T. Liao, C.-H. Duan, and S.-H. Lai
  - The 2010 Pacific-Rim Conference on Multimedia (PCM), Shanghai, China, 2010.
95. Binary orientation trees for volume and surface reconstruction from unoriented point clouds
  - Y.-L. Chen, B.-Y. Chen, S.-H. Lai and T. Nishita
  - Pacific Graphics (PG), Hangzhou, China, Sep. 2010
96. Content-Aware Geometry Image Resizing
  - S.-F. Wang, Y.-L. Chen, C.-K. Chiang and S.-H. Lai
  - Proc. Computer Graphics International(CGI), short paper, Singapore, June 2010.
97. Fast H.264 Encoding Based On Statistical Learning
  - C.-K. Chiang and S.-H. Lai
  - The 2010 Pacific-Rim Conference on Multimedia (PCM), Shanghai, China, 2010. (Oral) (bibtex)
  - @inproceedings{DBLP:conf/pcm/ChiangL10,
    author = {Chen-Kuo Chiang and Shang-Hong Lai},
    title = {Fast H.264 Encoding Based on Statistical Learning},
    booktitle = {PCM (2)},
    year = {2010},
    pages = {179-189},
    ee = {http://dx.doi.org/10.1007/978-3-642-15696-0_17},
    crossref = {DBLP:conf/pcm/2010-2},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
98. Image Compressibility Assessment and The Application of Structure-Preserving Image Retargeting
  - S.-F. Wang and S.-H. Lai
  - IEEE International Conference on Multimedia & Expo (ICME), Singapore, 2010. (Oral, Student Travel Grant Award)
99. Learning spatial weighting via quadratic programming for facial expression analysis
  - C.-T. Liao, H.-J. Chuang, C.-H. Duan, and S.-H. Lai
  - The third IEEE Workshop on CVPR for Human Communicative Behavior Analysis, San Francisco, California, USA, June 2010.
100. Manifold-based 3D face caricature generation with individualized facial feature extraction
  - S.-F. Wang and S.-H. Lai
  - Pacific Graphics (PG), Hangzhou, China, Sep. 2010
101. MRI motion artifact correction based on spectral extrapolation with generalized series
  - H.-R. Su, T.-Y. Lee, S.-H. Lai, and T.-C. Chang
  - IEEE International Conference on Image Processing (ICIP), Hong Kong, Sep. 2010.
102. Over-Segmentation Based Background Modeling and Foreground Detection with Shadow Removal by Using Hierarchical MRFs
  - T.-F. Su, Y.-L. Chen, and S.-H. Lai
  - The Tenth Asian Conference on Computer Vision (ACCV'10), Queenstown, New Zealand, Nov. 2010
103. Robust Fourier-Based Image Alignment with Gradient Complex Image
  - H.-R. Su, S.-H. Lai, Y.-H. Tsai
  - International Conf. on Pattern Recognition (ICPR), Istanbul, Turkey, Aug. 2010.
104. Temporally Consistent Depth Map Estimation from Stereo Video Sequences
  - C.-M. Cheng, L.-H. Chin, X.-A. Hsu and S.-H. Lai
  - International Conference on 3D Systems and Applications (3DSA), Tokyo, Japan, May 2010.
105. 2D expression-invariant face recognition with constrained optical flow
  - C.-K. Hsieh, S.-H. Lai, and Y.-C. Chen
  - International Conf. on Multimedia and Expo. (ICME), New York, USA, July 2009.
106. A hierarchical image kernel with application to pedestrian identification for video surveillance
  - C.-T. Liao, S.-H. Lai, and W.-H. Wang
  - IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, Nov. 2009.
107. A Novel Color Context Descriptor and Its Applications
  - C.-T. Liao, Y.-L. Wang, S.-H. Lai, and C.-T. Hsu
  - IEEE International Conference on Multimedia and Expo (ICME), NewYork, USA, 2009.
108. A novel robust kernel for applications to images
  - C.-T. Liao and S.-H. Lai
  - IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Taipei, Taiwan, April 2009.
109. Compensation of Motion Artifacts in MRI via Graph-Based Optimization
  - T.-Y. Lee, H.-R. Su, S.-H. Lai, and T.-c. Chang
  - IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009. (bibtex)
  - <a href="http://dx.doi.org/10.1109/CVPR.2009.5206615"> (DOI) </a>
110. Efficient multiple virtual view generation based on reduced depth stereo image for advanced autostereoscopic displays
  - C.-M. Cheng, S.-J. Lin, S.-H. Lai, and K. Lee
  - International Conf. on Multimedia and Expo. (ICME), New York, USA, July 2009.
111. Effieient NCC-based image matching based on novel hierarchical bounds
  - S.-D. Wei , W.-H. Pan and S.-H. Lai
  - Pacific-Rim Conference on Multimedia (PCM), Bangkok, Tailand, Dec. 2009
112. Face detection directly from H.264 compressed video with convolutional neural network
  - S.-S. Zhuang and S.-H. Lai
  - International Conference on Image Processing (ICIP), Cairo, Egypt, Nov. 2009.
113. Fast Multi-Reference Motion Estimation Via Statistical Learning For H.264/AVC
  - C.-K. Chiang and S.-H. Lai
  - IEEE International Conference on Multimedia & Expo (ICME), New York, 2009. (Oral) (bibtex) (pdf)
  - @inproceedings{DBLP:conf/icmcs/ChiangL09,
    author = {Chen-Kuo Chiang and Shang-Hong Lai},
    title = {Fast multi-reference motion estimation via statistical learning for H.264/AVC},
    booktitle = {ICME},
    year = {2009},
    pages = {61-64},
    ee = {http://dx.doi.org/10.1109/ICME.2009.5202436},
    crossref = {DBLP:conf/icmcs/2009},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
114. Fast Structure-Preserving Image Retargeting
  - S.-F. Wang and S.-H. Lai
  - IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Taipei, 2009.
115. Geodesic tree-based dynamic programming for fast stereo reconstruction
  - C.-H. Sin, C.-M. Cheng, S.-H. Lai, S.-Y. Yang
  - IEEE Embedded Computer Vision Workshop, Kyoto, Japan, Oct. 2009
116. Image deblurring by deblurring by exploiting inherent bi-level regions
  - P.-H. Huang, Y.-M. Lin, H.-L. Yang, and S.-H. Lai
  - International Conference on Image Processing (ICIP), Cairo, Egypt, Nov. 2009.
117. Image rectification for uncalibrated stereo video with varying camera motions and zooming effects
  - C.-M. Cheng, S.-H. Lai, and S.-H. Su
  - IAPR Conf. on Machine Vision Applications (MVA), Yokohama, Japan, May 2009.
118. Integrated expression-invariant face recognition with constrained optical flow
  - C.-K. Hsieh, S.-H. Lai, and Y.-C. Chen
  - Proc. Pacific-Rim Symposium on Image and Video Technology (PSIVT), Tokyo, Japan, Jan. 2009.
119. Learning partially-observed hidden conditional random fields for facial expression recognition
  - K.-Y. Chang, T.-L. Liu, and S.-H. Lai
  - Proc. IEEE Conf. on Computer Vision & Pattern Recognition (CVPR), Miami, Florida, USA, June 2009
120. Lung-tissue segmentation for ventilation evaluation in hyperpolarized 3-helium MRI
  - H.-R. Su, K.-C. Li, and S.-H. Lai
  - International Forum on Medical Imaging in Asia (IFMIA), Taipei, Taiwan, Jan. 2009.
121. Robust Surface Reconstruction from Defective Point Clouds by Using Orientation Inference and Volumetric Regularization
  - Y.-L. Chen, S.-H. Lai, and T. Nishita
  - In Proceedings of Siggraph Asia 2009 (Sketch).
122. Spatio-temporally consistent multi-view video synthesis for autostereoscopic displays
  - S.-J. Lin, C.-M. Cheng, and S.-H. Lai
  - Pacific-Rim Conference on Multimedia (PCM), Bangkok, Tailand, Dec. 2009
123. Surface Simplification by Image Retargeting
  - S.-F. Wang, Y.-L. Chen, C.-K. Chiang and S.-H. Lai
  - In Proceedings of Siggraph Asia 2009 (Sketch).
124. 3D Non-rigid Registration for MPU Implicit Surfaces
  - T.-Y. Lee and S.-H. Lai
  - CVPR'08 Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment (NORDIA), 2008 (slides)
125. A hybrid motion estimation approach based on normalized cross correlation for video compression
  - W.-H. Pan, S.-D. Wei, and S.-H. Lai
  - International Conference on Acoustics, Speech and Signal Processing (ICASSP), Las Vegas, USA, April 2008.
126. A Memory Effective Two-phase Approach for Large Scanned Surface Mesh Simplification
  - Y.-L. Chen and X. Zhang
  - In Proceedings of Shape Modeling International 2008 (SMI'08), New York, June 2008. (bibtex)
  - @inproceedings{Chen:smi08,
    author = {Yi-Ling Chen and Xiang Zhang},
    title = {A memory effective two-phase approach for large scanned
    surface mesh simplification},
    booktitle = {In Proceedings of Shape Modeling International 2008 (SMI'08)},
    year = {2008},
    pages = {275-276},
    }
127. A novel motion estimation method based on normalized cross correlation for video compression
  - S.-D. Wei, W.-H. Pan, and S.-H. Lai
  - Proc. Multimedia Modeling Conference (MMM), Kyoto, Japan, Jan. 2008. (SCI)
128. A novel robust kernel for appearance-based learning
  - C.-T. Liao and S.-H. Lai
  - International Conference on Pattern Recognition (ICPR), Tampa, Florida, U.S.A., Dec. 2008.
129. A statistical learning approach to vertebra detection and segmentation from spinal MRI
  - S.-H. Huang, S.-H. Lai, and C. Novak
  - IEEE International Symposium on Biomedical Imaging (ISBI), Paris, France, May 2008.
130. Efficient NCC-based image matching in Walsh-Hadamard domain
  - W.-H. Pan, S.-D. Wei, and S.-H. Lai
  - Proc. European Conference on Computer Vision (ECCV), Vol. 3, pp. 468-480, Marseille, France, Oct. 2008. (SCI) (NSC 96-2220-E-007-017)
131. Estimating 3D Face Model and Facial Deformation from a Single Image Based on Expression Manifold Optimization
  - S.-F. Wang and S.-H. Lai
  - In Proceedings of European Conference on Computer Vision (ECCV), Marseille, France, Oct. 2008.
132. Expressional face image analysis with constrained optical flow
  - C.-K. Hsieh, S.-H. Lai, and Y.-C. Chen
  - Proc. IEEE Conference on Multimedia and Exposition (ICME), Hannover, Germany, June 2008.
133. Fast Intermode Decision via Statistical Learning for H.264 Video Coding
  - W.-H. Pan, C.-K. Chiang, S.-H. Lai
  - International Multi-Media Modeling Conference (MMM), Tokyo, 2008. (bibtex)
  - @inproceedings{DBLP:conf/mmm/PanCL08,
    author = {Wei-Hau Pan and Chen-Kuo Chiang and Shang-Hong Lai},
    title = {Fast Intermode Decision Via Statistical Learning for H.264 Video Coding},
    booktitle = {MMM},
    year = {2008},
    pages = {329-337},
    ee = {http://dx.doi.org/10.1007/978-3-540-77409-9_31},
    crossref = {DBLP:conf/mmm/2008},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
134. Image deblurring with blur kernel estimation from a reference image patch
  - P.-H. Huang, Y.-M. Lin and S.-H. Lai
  - International Conf. on Pattern Recognition, Tampa, Florida, USA, Dec. 8-11, 2008.
135. Improved novel view synthesis from depth image with large baseline
  - C.-M. Cheng, S.-J. Lin, S.-H. Lai, and C. J. Yang
  - Proc. International Conference on Pattern Recognition (ICPR), Tampa, Florida, U.S.A., Dec. 2008.
136. Real-time video surveillance based on combining foreground extraction and human detection
  - H.-C. Zeng, S.-H. Huang and S.-H. Lai
  - Proc. Multimedia Modeling Conference, Kyoto, Japan, Jan. 2008.
137. Silhouette-Based Camera Calibration from Sparse Views under Circular Motion
  - P.-H. Huang, and S.-H. Lai
  - IEEE Conf. on Computer Vision & Pattern Recognition, Alaska, USA, Jun. 24-26, 2008. (bibtex)
  - @inproceedings{Huang:cvpr08,
    author = {Po-Hao Huang and Shang-Hong Lai},
    title = {Silhouette-based camera calibration from sparse views under circular motion},
    booktitle = {IEEE Computer Society Conference on Computer Vision
    and Pattern Recognition (CVPR'08)},
    year = {2008},
    }
138. Video-Based face Recognition Based on View Synthesis from 3D Face Model Reconstructed from a Single Image
  - C.-T. Liao, S.-F. Wang, Y.-J. Lu and S.-H. Lai
  - IEEE International Conference on Multimedia & Expo (ICME), Hannover, Germany, 2008.
139. A Partition-of-Unity Based Algorithm for Implicit Surface Reconstruction Using Belief Propagation
  - Y.-L. Chen and S.-H. Lai
  - In Proceedings of Shape Modeling International 2007 (SMI'07), Lyon, France, June 2007. (bibtex)
  - @inproceedings{Chen:smi07,
    author = {Yi-Ling Chen and Shang-Hong Lai},
    title = {A Partition-of-Unity Based Algorithm for Implicit Surface
    Reconstruction Using Belief Propagation},
    booktitle = {In Proceedings of Shape Modeling International 2007 (SMI'07)},
    year = {2007},
    pages = {147-155},
    }
140. A Robust kernel based on robust ρ-function
  - C.-T. Liao and S.-H. Lai
  - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hawaii, April 2007.
141. Adaptive foreground object extraction for real-time video surveillance with lighting variations
  - H.-C. Zeng and S.-H. Lai
  - Proc. International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hawaii, April 2007.
142. Adaptive Multi-Reference Downhill Simplex Search Based On Spatial-Temporal Motion Smoothness Criterion
  - W.-H. Pan, C.-K. Chiang, S.-H. Lai
  - IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2007. (bibtex) (pdf)
  - @inproceedings{DBLP:conf/icassp/PanCL07,
    author = {Wei-Hau Pan and Chen-Kuo Chiang and Shang-Hong Lai},
    title = {Adaptive Multi-Reference Downhill Simplex Search Based on Spatial-Temporal Motion Smoothness Criterion},
    booktitle = {ICASSP (1)},
    year = {2007},
    pages = {1181-1184},
    ee = {http://dx.doi.org/10.1109/ICASSP.2007.366124},
    crossref = {DBLP:conf/icassp/2007},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
143. Camera Calibration from Silhouettes Under Incomplete Circular Motion with a Constant Interval Angle
  - P.-H. Huang, and S.-H. Lai
  - 8th Asian Conf. on Computer Vision, Tokyo, Japan, Nov. 18-22, 2007.
144. Efficient intra mode decision via statistical learning
  - C. Huang and S.-H. Lai
  - Proc. Pacific-Rim Conf. on Multimedia, Hong Kong, Dec. 2007.
145. Efficient intra mode selection using image structure tensor for H.264/AVC
  - C. Hwang, S. Zhuang, and S.-H. Lai
  - Proc. International Conference on Image Processing, San Antonio, USA, Sep. 2007.
146. Efficient normalized cross correlation based on adaptive multilevel successive elimination
  - S.-D. Wei and S.-H. Lai
  - Proc. Asian Conference on Computer Vision (ACCV), Tokyo, Japan, Nov. 2007.
147. Expression-invariant face recognition with accurate optical flow
  - C.-K. Hsieh, S.-H. Lai, and Y.-C. Chen
  - Proc. Pacific-Rim Conf. on Multimedia, Hong Kong, Dec. 2007.
148. Fast normalized cross correlation based on adaptive multilevel winner update
  - S.-D. Wei and S.-H. Lai
  - Advances in Multimedia Information Processing – PCM 2007 Lecture Notes in Computer Science Volume 4810, 2007, pp 413-416 (bibtex) (pdf)
  - @inproceedings{DBLP:conf/pcm/WeiL07,
    author = {Shou-Der Wei and
    Shang-Hong Lai},
    title = {Fast Normalized Cross Correlation Based on Adaptive Multilevel
    Winner Update},
    booktitle = {PCM},
    year = {2007},
    pages = {413-416},
    ee = {http://dx.doi.org/10.1007/978-3-540-77255-2_48},
    crossref = {DBLP:conf/pcm/2007},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
    @proceedings{DBLP:conf/pcm/2007,
    editor = {Horace Ho-Shing Ip and
    Oscar C. Au and
    Howard Leung and
    Ming-Ting Sun and
    Wei-Ying Ma and
    Shi-Min Hu},
    title = {Advances in Multimedia Information Processing - PCM 2007,
    8th Pacific Rim Conference on Multimedia, Hong Kong, China,
    December 11-14, 2007, Proceedings},
    booktitle = {PCM},
    publisher = {Springer},
    series = {Lecture Notes in Computer Science},
    volume = {4810},
    year = {2007},
    isbn = {978-3-540-77254-5},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
149. Fast template matching by applying winner-update on Walsh-Hadamard domain
  - S.-D. Wei and S.-H. Lai
  - Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on , Vol, pp.I-1029- pp.I-1032 (bibtex) (pdf)
  - @inproceedings{DBLP:conf/icassp/WeiLL07,
    author = {Shou-Der Wei and
    Shao-Wei Liu and
    Shang-Hong Lai},
    title = {Fast Template Matching by Applying Winner-Update on Walsh-Hadamard
    Domain},
    booktitle = {ICASSP (1)},
    year = {2007},
    pages = {1029-1032},
    ee = {http://dx.doi.org/10.1109/ICASSP.2007.366086},
    crossref = {DBLP:conf/icassp/2007},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
    @proceedings{DBLP:conf/icassp/2007,
    title = {Proceedings of the IEEE International Conference on Acoustics,
    Speech, and Signal Processing, ICASSP 2007, April 15-20,
    2007, Honolulu, Hawaii, USA},
    booktitle = {ICASSP},
    publisher = {IEEE},
    year = {2007},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
150. Generalized MPU Implicits by Using Belief Propagation
  - Y.-L. Chen, S.-H. Lai and T.-Y. Lee
  - In Proceedings of the Sixth International Conference on 3D Digital Imaging and Modeling (3DIM'07), Montreal, Canada, August 2007. (bibtex)
  - @inproceedings{Chen:3dim07,
    author = {Yi-Ling Chen and Shang-Hong Lai and Tung-Ying Lee},
    title = {Generalized MPU Implicits Using Belief Propagation},
    booktitle = {In Proceedings of the Sixth International Conference on 3D Digital Imaging
    and Modeling (3DIM'07)},
    year = {2007},
    pages = {400-407},
    }
151. Iterative blind image motion deblurring via learning a no-reference image quality measure
  - W.-H. Lee, S.-H. Lai, and C.-L. Chen
  - Proc. International Conference on Image Processing (ICIP), San Antonio, USA, Sep. 2007.
152. Automatic multi-layer red-eye detection
  - P.-H. Huang, Y.-C. Chien, and S.-H. Lai
  - International Conf. on Image Processing, Atlanta, USA, Oct. 2006.
153. Contour-based structure from reflection
  - P.-H. Huang, and S.-H. Lai
  - IEEE Conf. on Computer Vision & Pattern Recognition, New York, USA, Jun. 17-22, 2006. (bibtex)
  - @inproceedings{Huang:cvpr06,
    author = {Po-Hao Huang and Shang-Hong Lai},
    title = {Contour-Based Structure from Reflection},
    booktitle = {IEEE Computer Society Conference on Computer Vision and Pattern
    Recognition (CVPR'06)},
    year = {2006},
    pages = {379-386},
    }
154. Efficient 3D face reconstruction from a single 2D image by combining statistical and geometrical information
  - S.-F. Wang and S.-H. Lai
  - In Proceedings of Asian Conference on Computer Vision (ACCV'06), Jan. 2006. (Oral)
155. Facial expression recognition based on supervised LLE analysis of optical flow and ratio image
  - Y.-K. Wu and S.-H. Lai
  - Proc. International Computer Symposium, Taipei, Taiwan, Nov. 2006.
156. Fast and optimal block motion estimation via adaptive successive elimination
  - S.-D. Wei, S.-W. Liu, and S.-H. Lai
  - Proc. International Conference on Image Processing (ICIP), Atlanta, USA, Oct. 2006.
157. Fast Multi-Reference Frame Motion Estimation via Downhill Simplex Search
  - C.-K. Chiang, H.-C. Fei and S.-H. Lai
  - IEEE International Conference on Multimedia & Expo (ICME), Canada, 2006. (bibtex) (pdf)
  - @inproceedings{DBLP:conf/icmcs/ChiangL06,
    author = {Chen-Kuo Chiang and Shang-Hong Lai},
    title = {Fast Multi-Reference Frame Motion Estimation via Downhill Simplex Search},
    booktitle = {ICME},
    year = {2006},
    pages = {121-124},
    ee = {http://doi.ieeecomputersociety.org/10.1109/ICME.2006.262584},
    crossref = {DBLP:conf/icmcs/2006},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
158. Learning-based interactive video retrieval system
  - C.-J. Wu, H.-C. Zeng, S.-H. Huang, S.-H. Lai, W.-H. Wang
  - Proc. IEEE Conference on Multimedia and Exposition (ICME), Toronto, Canada, July 2006.
159. Modified winner update with adaptive block partition for fast motion estimation
  - S.-D. Wei, S.-W. Liu, and S.-H. Lai
  - Proc. IEEE Conference on Multimedia and Exposition (ICME), Toronto, Canada, July 2006.
160. Robust local intervertebral disc alignment for spinal MRI
  - J. G. Reisman, J. Hoeppner, S. Huang, L. Zhang, S.-H. Lai, and C. L. Novak
  - Proc. SPIE Symposium on Medical Imaging: Image Processing, Vol. 6144, San Diego, California, Feb. 2006.
161. Winner update on Walsh-Hadamard domain for fast motion estimation
  - S.-W. Liu, S.-D. Wei, and S.-H. Lai
  - Proc. 18th International Conference on Pattern Recognition (ICPR), Hong Kong, August 20-24, 2006.
162. 3D Human Body Tracking from a Monocular Image Sequence
  - I-H. Ko and S.-H. Lai
  - Proc. International Conference on Systems & Signals, Kaohsiung, Taiwan, April 2005.
163. A novel blind motion deblurring algorithm for restoring an image with uniform motion blur
  - C.-Y. Lin and S.-H. Lai
  - IPPR Conference on Computer Vision, Graphics and Image Processing, Taiwan, Aug. 2005.
164. An SVM-based approach to detecting video with irregular camera motion
  - K.-Y. Chang and S.-H. Lai
  - Proc. the 12th International Conference on Neural Information Processing, Taipei, Oct. 2005
165. An SVM-based approach to detecting video with irregular camera motion
  - K.-Y. Chang and S.-H. Lai
  - Proc. 12th International Conference on Neural Information Processing, Taipei, Oct. 2005.
166. Audio-visual information fusion for SVM-based biometric verification
  - Y.-Y. Chen and S.-H. Lai
  - Proc. International Conf. Cellular Neural Networks and Applications, Hsinchu, Taiwan, May 2005.
167. Hausdorff distance based PCB inspection system with defect classification
  - C.-J. Chen, S.-H. Lai, W.-H. Lee, C.-Y. Lin, T. Ku, C.-H. Chen, and Y.-C. Chung
  - Proc. SPIE Conf. on Two and Three-Dimensional Methods for Inspection and Metrology, Boston, USA, Oct. 2005.
168. Hausdorff distance based PCB inspection system with defect classification
  - C.-J. Chen, S.-H. Lai, W.-H. Lee, C.-Y. Lin, T. Ku, C.-H. Chen, and Y.-C. Chung
  - Proc. SPIE Conf. on Two and Three-Dimensional Methods for Inspection and Metrology, Boston, USA, Oct. 2005.
169. Intelligent video management system
  - S.-H. Huang, Q.-J. Wu, K.-Y. Chang, H.-C. Lin, S.-H. Lai, Y.-S. Tsai, W.-H. Wang, C.-L. Chen, and G.
  - Proc. International Conf. Information Technology: Research and Education, Hsinchu, Taiwan, June 2005.
170. Learning-based shot transition detection
  - H.-C. Lin and S.-H. Lai
  - IPPR Conference on Computer Vision, Graphics and Image Processing, Taiwan, Aug. 2005.
171. Learning-based video fast-pan detection
  - H.-C. Lin, S.-H. Huang, and S.-H. Lai
  - Proc. International Conf. Information Technology: Research and Education, Hsinchu, Taiwan, June 2005.
172. Locating Facial Feature Points Using Support Vector Machines
  - C.-T. Liao, Y.-K. Wu, and S.-H. Lai
  - The 9th IEEE International Workshop on Cellular Neural Networks and Their Applications (CNNA 2005), Hsingchu, Taiwan, 2005.
173. Locating facial feature points using support vector machines
  - C.-T. Liao, Y.-K. Wu, and S.-H. Lai
  - Proc. International Conf. Cellular Neural Networks and Applications, Hsinchu, Taiwan, May 2005.
174. Optical PCB inspection system based on Hausdorff distance
  - C.-J. Chen, S.-H. Lai, S.-W. Liu, T. Ku, and S. Y.-C. Yeh
  - Proc. of SPIE Conf. on Machine Vision Applications in Industrial Inspection, San Jose, California, Jan. 2005.
175. Partitioned gradient Fisherface for face recognition under illumination variations
  - L.-N. Chu and S.-H. Lai
  - Proc. the 12th International Conference on Neural Information Processing, Taipei, Oct. 2005.
176. Partitioned gradient Fisherface for face recognition under illumination variations
  - L.-N. Chu and S.-H. Lai
  - Proc. 12th International Conference on Neural Information Processing, Taipei, Oct. 2005.
177. Reliable image matching via modified Hausdorff distance with normalized gradient consistency measure
  - C. H. Yang, S.-H. Lai, and L. W. Chang
  - Proc. International Conf. Information Technology: Research and Education, Hsinchu, Taiwan, June 2005.
178. Robust metric structure from motion for an extended sequence with outliers and missing data
  - C.-M. Cheng, P.-H. Huang, and S.-H. Lai
  - ICCV BenCOS Workshop (Towards Benchmarking Automated Calibration, Orientation and Surface Reconstruction from Images), Beijing, China, Oct.15, 2005.
179. Robust metric structure from motion for an extended sequence with outliers and missing data
  - C.-M. Cheng, P.-H. Huang, and S.-H. Lai
  - ICCV BenCOS Workshop (Towards Benchmarking Automated Calibration, Orientation and Surface Reconstruction from Images), Beijing, China, Oct.15, 2005.
180. Speech-Driven Mouth Animation Based on Support Vector Regression
  - C.-T. Liao, Y.-K. Wu, and S.-H. Lai
  - The 10th Conference on Artificial Intelligence and Applications (TAAI), Kaohsiung, Taiwan, 2005.
181. Speech-driven mouth animation based on support vector regression
  - C.-T. Liao, Y.-K. Wu, and S.-H. Lai
  - Proc. 10th Conference on Artificial Intelligence and Applications, Kaohsiung, Dec. 2005.
182. Three-dimensional model reconstruction for treasures of jadeite material from uncalibrated image sequences
  - C.-M. Cheng, S.-F. Wang, C.-H. Teng, P.-H. Huang, Y.-C. Chien, and S.-H. Lai
  - In Proceedings of SPIE Conf. on Videometrics, San Jose, California, Jan. 2005.
183. Three-dimensional model reconstruction for treasures of jadeite material from uncalibrated image sequences
  - C.-M. Cheng, S. F. Wang, C.-H. Teng, P.-H. Huang, Y.-C. Chien, and S.-H. Lai
  - Proc. SPIE Conf. on Videometrics, San Jose, California, Jan. 2005.
184. A PCA based approach to facial feature extraction
  - S.-H. Lai , J.-G. Chen, and Y.-S. Huang
  - IPPR Conference on Computer Vision, Graphics and Image Processing, Taiwan, Aug. 2004.
185. A robust and efficient video stabilization algorithm
  - H.-C. Chang, S.-H. Lai, and K.-R. Lu
  - International Conf. on Multimedia and Expo., Taipei, Taiwan, June 2004.
186. An accurate and adaptive optical flow estimation algorithm
  - C.-H. Teng, S.-H. Lai, Y. S. Chen, W.-H. Hsu
  - International Conference on Image Processing, Singapore, Oct. 2004.
187. Detecting faces from color video by using paired wavelet features
  - S.-H. Huang and S.-H. Lai
  - Proc. first IEEE Workshop on Face Processing in Video, Washington, D.C., USA, June 2004.
188. Real-time face detection in color video
  - S.-H. Huang and S.-H. Lai
  - the 10th International Multi-Media Modelling Conference, Brisbane, Australia, January 5-7, 2004.
189. Robust 2D-3D pose estimation from noisy data
  - C.-M. Cheng and S.-H. Lai
  - IPPR Conference on Computer Vision, Graphics and Image Processing, Taiwan, Aug. 2004.
190. Robust 3D object model reconstruction from video
  - P.-H. Huang, Y.-L. Chen, C.-M. Cheng, Y.-A. Lu and S.-H. Lai
  - In Proceedings of SPIE Conference on Three-Dimensional Image Capture and Applications VI, San Jose, California, U.S.A., Jan. 2004.
191. Robust 3D object model reconstruction from video
  - P.-H. Huang, Y.-L. Chen, C.-M. Cheng, Y.-A. Lu, and S.-H. Lai
  - Proc. SPIE Conf. on Three-Dimensional Image Capture and Applications VI, San Jose, California, Jan. 2004.
192. Robust camera motion estimation and classification for video analysis
  - H.-C. Chang and S.-H. Lai
  - Proc. SPIE Conf. on Visual Communication and Image Processing, (EI) San Jose, California, Jan. 2004.
193. Robust face recognition under lighting variations
  - S.-D. Wei and S.-H. Lai
  - International Conference on Pattern Recognition, Cambridge, UK, Aug. 2004.
194. A PDM Based Approach to Recovering 3D Face Pose and Structure from Video
  - C. M. Cheng, S.-H. Lai, and K. Y. Chang
  - International Conference on Information Technology: Research and Education, August 10-13, 2003, Newark, New Jersey, USA.
195. Integrated video shot segmentation algorithm
  - W.-K. Li and S.-H. Lai
  - SPIE Conf. on Storage and Retrieval for Media Databases, Santa Clara, California, Jan. 2003.
196. Learning a statistical 3D geometric head model
  - S.-H. Lai and Y.-L. Chen
  - In Proceedings of SPIE Conference on Videometrics VII, Santa Clara, California, U.S.A., Jan. 2003.
197. Learning a statistical 3D geometric head model
  - S.-H. Lai and Y.-L. Chen
  - SPIE Conf. on Videometrics, Santa Clara, California, Jan. 2003.
198. Reliable Face Recognition Based on Matching Normalized Gradients
  - C. H. Yang, S.-H. Lai, and L. W. Chang
  - International Conference on Information Technology: Research and Education, August 10-13, 2003, Newark, New Jersey, USA.
199. New video shot change detection algorithms based on accurate motion and illumination estimation
  - S.-H. Lai and W.-K. Li
  - Proc. SPIE Conf. On Storage and Retrieval for Media Databases, Vol. 4676, pp. 148-157, San Jose, California, Jan. 2002.
200. Reliable image matching based on relative gradients
  - S.-H. Lai and S.-D. Wei
  - Proc. Of International Conference on Pattern Recognition, Vol. 2, pp. 802-805, Quebec City, Canada, Aug. 2002.
201. Robust computation of optical flow under non-uniform illumination variations
  - C.-H. Teng, S.-H. Lai, Y. S. Chen, W.-H. Hsu
  - Proc. Of International Conference on Pattern Recognition, Vol. 1, pp. 327-330, Quebec City, Canada, Aug. 2002.
202. Robust face matching under different lighting conditions
  - C.-H. T. Yang, S.-H. Lai and L.-W. Chang
  - Proc. International Conference on Multimedia and Expo., Lausanne, Switzerland, Aug. 2002.
203. 3D Head Model Reconstruction from Video
  - S.-H. Lai and C.-M. Cheng
  - Workshop on the 21st Century Digital Life and Internet Technologies, Tainan, Taiwan, May 2001.
204. An Integrated Approach to 3D Face Model Reconstruction from Video
  - C.-M. Cheng and S.-H. Lai
  - Proc. of the Second International Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems (RATFG-RTS 2001), pp.16-23, Vancouver, Canada, July 2001.
205. Computing Individualized 3D Face Model from an Image Sequence
  - C.-M. Cheng and S.-H. Lai
  - 14th IPPR Conference on Computer Vision, Graphics and Image Processing, Kending, Taiwan, Aug. 2001.
206. Efficient hybrid search algorithm for accurate image alignment under nonuniform illumination variations
  - S.-H. Lai and M. Fang
  - Proc. of SPIE Conf. on Machine Vision Applications in Industrial Inspection, Vol. 4301, San Jose, California, Jan. 2001.
207. Three-dimensional Face Model Creation from Video
  - S.-H. Lai and C.-M. Cheng
  - Proc. of SPIE Conf. on Three-dimensional Image Capture and Applications IV, Vol. 4298, San Jose, Jan. 2001.
208. Adaptive motion estimation for image sequences under non-uniform illumination variations
  - S.-H. Lai
  - Proceedings of International Computer Symposium: Workshop on Image Processing and Pattern Recognition, pp.223-230, Chiayi, Taiwan, Dec. 2000.
209. Incomplete Cholesky Preconditioning for Early Vision
  - S.-H. Lai
  - Proceedings of the Fourth Asian Conference on Computer Vision, pp. 318-323, Taipei, Taiwan, Jan. 2000.
210. A FLASH system for fast and accurate pattern localization
  - S.-H. Lai and M. Fang
  - Proceedings of SPIE Conf. on Machine Vision Applications in Industrial Inspection VII, Vol. 3652, pp. 164-173, San Jose, California, Jan. 25-27, 1999.
211. A novel illumination compensation algorithm for industrial inspection
  - S.-H. Lai and M. Fang
  - Proceedings of SPIE Conf. on Machine Vision Applications in Industrial Inspection VII, Vol. 3652, pp. 50-58, San Jose, California, Jan. 25-27, 1999.
212. Robust and efficient image alignment with spatially-varying illumination models
  - S.-H. Lai and M. Fang
  - Proceedings of IEEE Conference on Computer Vision & Pattern Recognition, Vol. 2, pp. 167-172, Fort Collins, Colorado, June 23-25, 1999.
213. Total variational blind image restoration from image sequences
  - S.-H. Lai and Y. Cui
  - Proceedings of SPIE Conf. on Visual Communications and Image Processing, Vol. 3653, pp. 96-105, San Jose, California, Jan. 25-27, 1999.
214. A neural network based system for optimal medical image visualization with fast online adaptation capabilities
  - S.-H. Lai and M. Fang
  - Proceedings of the 32nd Annual Conference on Information Sciences and Systems, Princeton, New Jersey, Mar. 1998.
215. A new variational shape-from-orientation approach to correcting intensity inhomogeneities in MR images
  - S.-H. Lai and M. Fang
  - Proceedings of IEEE Workshop on Biomedical Image Analysis, pp. 56-63, Santa Barbara, California, June 1998.
216. A novel local PCA based method for detecting activation signals in fMRI
  - S.-H. Lai and M. Fang
  - Proceedings of SPIE Symposium on Medical Imaging: Physiology and Function from Multidimensional Images, Vol. 3337, pp. 327-338, San Diego, California, Feb. 1998. San Diego, California, Feb. 1998.
217. Adaptive medical image visualization based on hierarchical neural networks and intelligent decision fusion
  - S.-H. Lai and M. Fang
  - Proceedings of the IEEE Workshop on Neural Networks for Signal Processing, pp. 438-447, Cambridge, England, Aug. 1998.
218. Intensity inhomogeneity correction for surface-coil MR images by image fusion
  - S.-H. Lai and M. Fang
  - Proceedings of the International Conference on Multisource-Multisensor Information Fusion, pp. 880-887, Las Vegas, Nevada, July 1998.
219. Robust and automatic adjustment of display window width and center for MR images
  - S.-H. Lai and M. Fang
  - Proceedings of SPIE Symposium on Medical Imaging: Image Perception, Vol. 3340, pp. 105-116, San Diego, California, Feb. 1998.
220. A Fourier transform method for detecting fMRI activation signals
  - M. Fang, S.-H. Lai and E. Mueller
  - Proceedings of the Third International Conference on Functional Mapping of the Human Brain, Copenhagen, Denmark, May, 1997.
221. A local PCA based method for detecting fMRI activation signals
  - S.-H. Lai, M. Fang and E. Mueller
  - Proceedings of the Third International Conference on Functional Mapping of the Human Brain, Copenhagen, Denmark, May, 1997.
222. Physically-based adaptive preconditioners for early vision
  - S.-H. Lai and B.C. Vemuri
  - Proceedings of the IEEE Workshop on Physics-based Modeling in Computer Vision, pp. 151-157, MIT, Cambridge, June, 1995.
223. Robust and efficient algorithms for optical flow computation
  - S.-H. Lai and B.C. Vemuri
  - Proceedings of the IEEE International Symposium on Computer Vision, pp. 455-460, Coral Gables, Florida, Nov., 1995.
224. An O(N) iterative solution to the Poisson equations in low-level vision problems
  - S.-H. Lai and B.C. Vemuri
  - Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 9-14, Seattle, June, 1994.
225. A fast solution to the surface reconstruction problem
  - B.C. Vemuri and S.-H. Lai
  - SPIE's Annual International Symposium: Geometric Methods in Computer Vision, pp. 27-37, San Diego, July, 1993.
226. Construction of occlusion boundary for stroke segmentation
  - F. Chang and S.-H. Lai
  - Proceedings of the Third National Conference on Computer Vision & Image Processing, Taiwan, 1991.
227. 3-D object motion parameters estimation via Hadamard transform
  - S.-H. Lai and S. Chang
  - Proceedings of the Second International Conference on the Advances of Communication and Control Systems, pp. 1380-1390, Baton Rouge, Louisiana, USA, 1988.
228. A generalized method for extracting depth from one image
  - S.-H. Lai, C. W. Fu and S. Chang
  - Proceedings of National Symposium on Automatic Control, pp. 398-407, Taiwan, 1988.
229. Estimation of two-dimensional translation via Hadamard transform
  - S.-H. Lai and S. Chang
  - Signal Processing IV: Theories & Applications, Proceedings of the Fourth European Conference on Signal Processing, vol. 1, pp. 35-37, Grenoble, France, 1988
230. Estimation of 3-D translational motion parameters via Hadamard transform
  - S.-H. Lai and S. Chang
  - Proceedings of National Symposium on Automatic Control, pp. 160-169, Taiwan, 1987
Patents
1. 臉部表情辨識系統及其辨識方法及其電腦程式產品
  - 王文男、賴尚宏、廖家德、莊蕙如、蔡子宸、張芳凱
  - 中華民國發明第I430185專利，Mar. 2014
2. Hierarchical motion deblurring method for single image
  - H.-L. Yang, P.-H. Huang, S.-H. Lai, C.-C. Huang, and S.-H. Yu
  - US patent 8509559, Aug. 2013
3. Method of motion estimation for video compression
  - C.-K. Chiang, H. C. Fei, and S.-H. Lai
  - US patent 8422557, April 2013
4. 單張影像的階層式去動態模糊方法
  - 楊皓量、黃柏豪、賴尚宏、黃至治、游舒涵
  - 中華民國發明第 I405147 專利，Aug. 2013.
5. 照片分割方法及系統及照片之影像配合方法
  - 賴尚宏、蔡依婷、黃思皓
  - 中華民國發明第 I396143 專利，May 2013
6. 臉部辨識方法
  - 賴尚宏、廖家德
  - 中華民國發明第I382354專利，Jan. 2013.
7. Compressibility-aware media retargeting with structure preserving
  - S.-H. Lai and S.-F. Wang
  - US patent 8295647, Oct. 2012
8. Face recognition by fusing similarity probability
  - S.-H. Lai and C.-T. Liao
  - US patent 8300900, Oct. 2012
9. Method and system for automatic figure segmentation
  - S.-H. Lai , I.-T. Tsai, and S.-H. Huang
  - US patent 8306333, Nov. 2012
10. 用於影像壓縮之移動預估方法
  - 江振國、費懷忠、賴尚宏
  - 中華民國發明第 I345915 專利，July 2011
11. System and method for detecting intervertebral disc alignment using vertebrae segmentation
  - S.-H. Lai, B. Odry, and L. Zhang
  - US patent 7804986, Sep. 2010
12. Statistical facial feature extraction method
  - S.-H. Lai, J.-G.. Chen, and Y.-S. Huang
  - US Patent 7372981, May 2008
13. Video stabilization method
  - S.-H. Lai, H.-C. Chang, and K.-R. Lu
  - US Patent 7440008, Oct. 2008
14. Method of Motion Estimation for Image Compression
  - C.-K. Chiang, H.-C. Fei and S.-H. Lai
  - US Pending Patent
15. System and method for detecting intervertebral disc alignment using vertebrae segmentation
  - S.-H. Lai, B. Odry, and L. Zhang
  - filed for US patent, 2006
16. 視訊穩定方法及其電腦可讀取媒體
  - 賴尚宏、張宏彰、陸光榮
  - 中華民國發明第 I253002 專利，2006.
17. 統計式臉部特徵抽取方法
  - 賴尚宏、陳建志、黃雅軒
  - 中華民國發明第 I226589 專利，Jan. 2005
18. Method for image alignment under non-uniform illumination variations
  - S.-H. Lai and M. Fang
  - US Patent 6.744,933, June 2004
19. Flash system for fast and accurate pattern localization
  - S.-H. Lai and M. Fang
  - US Patent 6,546,137, April 2003
20. Method for matching images using spatially-varying illumination change models
  - S.-H. Lai and M. Fang
  - US Patent 6,621,929, Sep. 2003
21. Illumination compensation system for industrial inspection
  - S.-H. Lai and M. Fang
  - US Patent 6,445,812, Sep. 2002
22. Total variational blind image restoration from image sequences
  - S.-H. Lai and Y. Cui
  - US Patent 6,470,097, Oct. 2002
23. Bias field estimation for intensity inhomogeneity correction in MR images
  - S.-H. Lai and M. Fang
  - US Patent 6,208,138, Mar. 2001
24. Method of localization refinement of pattern images using optical flow constraints
  - S.-H. Lai and M. Fang
  - US Patent 6,330,353, Dec. 2001
25. Neural network based auto-windowing system for MR images
  - S.-H. Lai and M. Fang
  - US Patent 6,175,643, Jan. 2001
26. Local principal component analysis based method for detecting activation signals in functional MR images
  - S.-H. Lai and M. Fang
  - US Patent 5,887,074, Mar. 1999
27. Robust and automatic adjustment of display window width and center for MR images
  - S.-H. Lai and M. Fang
  - US Patent 5,995,644, Nov. 1999
Book Chapters
1. Computer Vision – ACCV 2016 (1)
  - Shang-Hong Lai, Vincent Lepetit, Ko Nishino, Yoichi Sato
  - (ISBN: 978-3-319-54189-1). Springer International Publishing. 2017.
2. Automatic detection and removal of visible image watermarks
  - 9. H.-R. Su, Y.-Y. Cheng, S.-H. Lai
  - Multimedia Security: Watermarking, Steganography, and Forensics, CRC Press
3. Accurate facial feature localization on expressional face images based on a graphical model approach
  - C.-T. Liao C.-H. Duan and S.-H. Lai
  - Advances in Multimedia Information Processing – PCM 2010, LNCS 6298, pp. 672-681, 2011
4. Fast H.264 Encoding Based on Statistical Learning
  - C.-K. Chiang, S.-H. Lai
  - Advances in Multimedia Information Processing, LNCS 6298, pp. 179-189, Springer 2011 (bibtex)
  - @article{DBLP:journals/tcsv/ChiangPHZL11,
    author = {Chen-Kuo Chiang and
    Wei-Hau Pan and
    Chiuan Hwang and
    ShinShan Zhuang and
    Shang-Hong Lai},
    title = {Fast H.264 Encoding Based on Statistical Learning},
    journal = {IEEE Trans. Circuits Syst. Video Techn.},
    volume = {21},
    number = {9},
    year = {2011},
    pages = {1304-1315},
    ee = {http://dx.doi.org/10.1109/TCSVT.2011.2147250},
    bibsource = {DBLP, http://dblp.uni-trier.de}
    }
5. People localization in a camera network combining background subtraction and scene-aware human detection
  - T.-Y. Lee, T.-Y. Lin, S.-H. Huang, S.-H. Lai
  - Advances in Multimedia Modeling, LNCS 6523, pp. 151-160, 2011
6. Effieient NCC-based image matching based on novel hierarchical bounds
  - S.-D. Wei , W.-H. Pan and S.-H. Lai
  - Advances in Multimedia Information Processing – PCM 2009, LNCS 5879, pp. 807-815, 2009
7. Spatio-temporally consistent multi-view video synthesis for autostereoscopic displays
  - S.-J. Lin, C.-M. Cheng, and S.-H. Lai
  - Advances in Multimedia Information Processing – PCM 2009, LNCS 5879, pp. 532-542, 2009
8. A novel motion estimation method based on normalized cross correlation for video compression
  - S.-D. Wei, W.-H. Pan, and S.-H. Lai
  - Advances in Multimedia Modeling, LNCS 4903, pp. 338-347, 2008
9. Fast intermode decision via statistical learning for H.264 video coding
  - W.-H. Pan, C.-K. Chiang, and S.-H. Lai
  - Advances in Multimedia Modeling, LNCS 4903, pp. 329-337, 2008
10. Real-time video surveillance based on combining foreground extraction and human detection
  - H.-C. Zeng, S.-H. Huang and S.-H. Lai
  - Advances in Multimedia Modeling, LNCS 4903, pp. 70-79, 2008
11. Efficient intra mode decision via statistical learning
  - C. Huang and S.-H. Lai
  - Advances in Multimedia Information Processing – PCM 2009, LNCS 4810, pp. 148-157, 2007
12. Expression-invariant face recognition with accurate optical flow
  - C.-K. Hsieh, S.-H. Lai, and Y.-C. Chen
  - Advances in Multimedia Information Processing – PCM 2009, LNCS 4810, pp. 78-87, 2007
13. Fast normalized cross correlation based on adaptive multilevel winner update
  - S.-D. Wei and S.-H. Lai
  - Advances in Multimedia Information Processing – PCM 2009, LNCS 4810, pp. 413-416, 2007
14. Reproducibility Analysis of Event-Related fMRI Experiments Using Laguerre Polynomials
  - H.-R. Su, M. Liou, P. E. Cheng, J. A. D. Aston, and S.-H. Lai
  - Neural Information Processing, LNCS, Volume 4984, pp. 126-134, 2007.
15. Temporally integrated pedestrian detection from non-stationary video
  - C.-J. Wu and S.-H. Lai
  - Advanced in Multimedia Modeling, Lecture Notes in Computer Science, Volume 4351, pp. 188-197, Springer-Verlag, 2007. (SCI)
16. Adaptive object tracking with online statistical model update
  - K.-Y. Chang and S.-H. Lai
  - Lecture Notes in Computer Science, Volume 3852, pp. 363 - 372, Springer-Verlag, 2006. (SCI)
17. Efficient 3D face reconstruction from a single 2D image by combining statistical and geometrical information
  - S.-F. Wang and S.-H. Lai
  - Lecture Notes in Computer Science, Volume 3852, pp. 427 - 436, Springer-Verlag, 2006. (SCI)
18. Enhanced downhill simplex search for fast video motion estimation
  - H.-C. Fei, C.-J. Chen, and S.-H. Lai
  - Lecture Notes in Computer Science, Volume 3767, pp. 512 - 523, Springer-Verlag, 2005
19. Improved Adaboost-based image retrieval with relevance feedback via paired feature learning
  - S.-H. Huang, Q.-J. Wu, and S.-H. Lai
  - Lecture Notes in Computer Science, Volume 3568, pp. 660-670, Springer-Verlag, 2005
20. A motion-aided video shot segmentation algorithm
  - W.-K. Li and S.-H. Lai
  - Advanced in Multimedia Information Processing, LNCS 2532, pp. 336-343, Springer-Verlag, 2002
21. An Efficient Algorithm for Detecting Faces from Color Images
  - S.-D. Wei and S.-H. Lai
  - in Advanced in Multimedia Information Processing, LNCS 2532, pp. 1177 - 1184 , Springer-Verlag, 2002
22. An illumination-insensitive face matching algorithm
  - C.-H. T. Yang, S.-H. Lai and L.-W. Chang
  - in Advanced in Multimedia Information Processing, LNCS 2532, pp. 1185-1192, Springer-Verlag, 2002
23. Functional MR image analysis
  - S.-H. Lai and M. Fang
  - Signal Processing for Magnetic Resonance Imaging and Spectroscopy, ed. H. Yan, Marcel Dekker Pub., 2002
24. Fast algorithms for fitting multiresolution hybrid shape models to brain MRI
  - B.C. Vemuri, Y. Guo, S.-H. Lai and C.M. Leonard
  - Visualization in Biomedical Computing, Lecture Notes in Computer Science, Volume 1131, pp. 213-222, Springer-Verlag, 1996

Journal Papers

2021 - Journal Papers

2020 - Journal Papers

2019 - Journal Papers

2017 - Journal Papers

2016 - Journal Papers

2015 - Journal Papers

2014 - Journal Papers

2013 - Journal Papers

2012 - Journal Papers

2011 - Journal Papers

2010 - Journal Papers

2009 - Journal Papers

2008 - Journal Papers

2007 - Journal Papers

2006 - Journal Papers

2005 - Journal Papers

2004 - Journal Papers

2003 - Journal Papers

2002 - Journal Papers

2001 - Journal Papers

2000 - Journal Papers

1999 - Journal Papers

1998 - Journal Papers

1997 - Journal Papers

1996 - Journal Papers

1995 - Journal Papers

1992 - Journal Papers

1988 - Journal Papers

Local Journal Papers

2009 - Local Journal Papers

2007 - Local Journal Papers

2004 - Local Journal Papers

2002 - Local Journal Papers

2001 - Local Journal Papers

Conference Papers

2022 - Conference Papers

2021 - Conference Papers

2020 - Conference Papers

2019 - Conference Papers

2018 - Conference Papers

2017 - Conference Papers

2016 - Conference Papers

2015 - Conference Papers

2014 - Conference Papers

2013 - Conference Papers

2012 - Conference Papers

2011 - Conference Papers

2010 - Conference Papers

2009 - Conference Papers

2008 - Conference Papers

2007 - Conference Papers

2006 - Conference Papers

2005 - Conference Papers

2004 - Conference Papers

2003 - Conference Papers

2002 - Conference Papers

2001 - Conference Papers

2000 - Conference Papers

1999 - Conference Papers

1998 - Conference Papers

1997 - Conference Papers

1995 - Conference Papers

1994 - Conference Papers

1993 - Conference Papers

1991 - Conference Papers

1988 - Conference Papers

1987 - Conference Papers

Patents

2014 - Patents

2013 - Patents

2012 - Patents

2011 - Patents

2010 - Patents

2008 - Patents

2007 - Patents

2006 - Patents

2005 - Patents

2004 - Patents

2003 - Patents