電腦視覺前瞻研究國際研討會

August 15th
Evergreen International Hotels (Keelung), Taiwan

NEW! Some of the slide files for the talks are provided in the Program part.


About

ACCV 2016將於今年十一月於台北國際會議中心舉辨，八月中在台北舉行議程委員會議，屆時將有近四十位國際知名電腦視覺專家學者造訪台灣，CVGIP將於會議第一天(8/15)在大會場地(基隆長榮桂冠酒店)與ACCV共同舉辦電腦視覺高峰論壇，邀請廿餘位知名電腦視覺學者和與會貴賓分享他們最新的研究成果，內容精彩可期，歡迎報名參加，同時報名CVGIP與該論壇可享折扣，報名細節將於近日公布，敬請期待。<>

Program

There are total four sessions in this workshop.

1. Deep Learning
2. Visual Learning
3. Visual Understanding
4. Geometry and Imaging
Learn more...

PROGRAM SCHEDULE

August 15th, 2016

08:30-09:20 Registration
09:20-09:30 Opening
09:30-10:45 Session on Deep Learning
· Deep Structured Models for Group Activities and Label Hierarchies (Greg Mori)
· Automatic Image Colorization and Rough Sketch Cleanup by Deep Learning (Hiroshi Ishikawa)
· Interpreting Neural Semantics in Deep Models (Xiaogang Wang)
· Very Deep Super Resolution (Kyoung Mu Lee)
· Visual Learning of Arithmetic Operations (Shmuel Peleg)
10:45-11:15 Coffee Break
11:15-12:15 Session on Visual Learning
· Unsupervised Learning of Object Representations from Geodesic Space Clustering of Disparate Views (Narendra Ahuja)
· Seing Through the Clouds (Raquel Urtasun)
· ProCRC: A Probabilistic Collaborative Representation based Classifier (Lei Zhang)
· Visual Turing Test & Visual Physics (Mario Fritz)
12:15-14:00 Lunch
14:00-15:15 Session on Visual Understanding
· Modeling context between objects for understanding referring expressions (Larry Davis)
· Leveraging external knowledge in Visual Questions Answering (Anton van den Hengel)
· Video Title Generation (Min Sun)
· Towards Understanding Stories in Videos (Sanja Fidler)
· Beyond Sharing Weights for Deep Domain Adaptation (Mathieu Salzmann)
15:15-15:45 Coffee Break
15:45-17:00 Session on Geometry and Imaging
· LIFT: Learned Invariant Feature Transform (Vincent Lepetit)
· SeetaFace: an Open Source Face Recognition Engine (Shiguang Shan)
· Unsupervised learning for single-view depth estimation: geometry to the rescue (Ian Reid)
· Semi-calibrated Photometric Stereo (Yasuyuki Matsushita)
· Deep Learning for SLAM? (Yasutaka Furukawa)
· Programmable Automotive Headlights: High Performance Lighting and Imaging at 100 miles per hour (Srinivasa Narasimhan)

Speakers

Narendra Ahuja USA

UIUC

Larry Davis USA

U. of Maryland

Sanja Fidler Canada

U. of Toronto

Mario Fritz Germany

Max Planck Institute for Informatics

Yasutaka Furukawa USA

Washington U. in St. Louis

Hiroshi Ishikawa Japan

Waseda U.

Iasonas Kokkinos France

CentraleSupélec/INRIA

Kyoung Mu Lee Korea

Seoul National U.

Yasuyuki Matsushita Japan

Osaka U.

Greg Mori Canada

Simon Fraser U.

Srinivasa Narasimhan USA

CMU

Shmuel Peleg Israel

Hebrew U. of Jerusalem

Ian Reid Australia

U. of Adelaide

Mathieu Salzmann Switzerland

EPFL

Shiguang Shan China

Chinese Academy of Sciences

Min Sun Taiwan

National Tsing Hua U.

Raquel Urtasun Canada

U. of Toronto

Anton van den Hengel Australia

U. of Adelaide

Xiaogang Wang Hong Kong

Chinese U. of Hong Kong

Lei Zhang Hong Kong

Hong Kong Poly U.

Committee


王鈺強 中央研究院資訊科技創新研究中心
林彥宇 中央研究院資訊科技創新研究中心
林惠勇 國立中正大學電機工程學系
洪一平 國立台灣大學資訊工程學系
徐繼聖 國立台灣科技大學機械工程系
孫 民 國立清華大學電機工程學系
莊永裕 國立台灣大學資訊工程學系
莊仁輝 國立交通大學資訊工程學系
陳煥宗 國立清華大學資訊工程學系
陳祝嵩 中研究院資訊科學研究所
陳永昇 國立交通大學資訊工程學系
陳冠文 國立交通大學資訊工程學系
黃于飛 國立宜蘭大學資訊工程研究所
詹寶珠 國立成功大學電機工程學系
劉庭祿       中央研究院資訊科學研究所

Organizer

賴尚宏 Taiwan

國立清華大學資訊工程學系

lai@cs.nthu.edu.tw

Location

Evergreen International Hotels (Keelung), Taiwan

No. 62-1, Zhongzheng Rd., Keelung, 202

Contact

For any inquiries, please email at:

skyand55@gmail.com (何天與)