The joint VCL-ViSU 2009 workshop June 2009 - Miami Beach, Florida
VCL'09 - Keynote Speaker:
VCL'09 - Invited Talk:
VCL'09 - Keynote:
VCL'09 - Industry Talk:
VCL'09 - Short Presentation 1:
Using Closed Captions to Train Activity Recognizers that Improve Video Retrieval
Authors:
Sonal Gupta (University of Texas at Austin), Raymond Mooney (University of Texas at Austin)
VCL'09 - Short Presentation 2:
Talking Pictures: Temporal Grouping and Dialog-Supervised Person Recognition in Video
Authors:
Timothee Cour (University of Pennsylvania), Benjamin Sapp (University of Pennsylvania), Akash Nagle (University of Pennsylvania), Ben Taskar (University of Pennsylvania)
VCL-ViSU'09 Spotlights:
Multiple label prediction for image annotation with multiple kernel correlation models
Authors:
Oksana Yakhnenko (Iowa State University), Vasant Honavar (Iowa State University)
HANOLISTIC: A Hierarchical Automatic Image Annotation System Using Holistic Approach
Authors:
Özge Öztimur Karadağ (Metu), Fatoş Yarman Vural (metu)
Categorization in Natural Time-Varying Image Sequences
Authors:
Teresa Ko (UCLA), Stefano Soatto (UCLA), Deborah Estrin (UCLA)
Scenes vs. Objects: a Comparative Study of Two Approaches to Context Based Recognition
Authors:
Andrew Rabinovich (Google), Serge Belongie (UCSD)
Mining Discriminative Adjectives and Prepositions for Natural Scene Recognition
Authors:
Bangpeng Yao (Princeton University), Juan Carlos Niebles (Princeton University), Li Fei-Fei (Princeton University)
VCL-ViSU Poster Session:
Adaptive Object Classification in Surveillance System by Exploiting Scene Context
Authors:
Jitao Sang (CASIA), Zhen Lei (CBSR, CASIA), Shengcai Liao (NLPR, Institute of Automation, Chinese Academy of Sciences), Stan Li (CBSR, CASIA)
Multiple label prediction for image annotation with multiple kernel correlation models
Authors:
Oksana Yakhnenko (Iowa State University), Vasant Honavar (Iowa State University)
HANOLISTIC: A Hierarchical Automatic Image Annotation System Using Holistic Approach
Authors:
Özge Öztimur Karadağ (Metu), Fatoş Yarman Vural (metu)
Combining Appearance and Motion for Human Action Classification in Videos
Authors:
Paramveer S. Dhillon (University of Pennsylvania), Sebastian Nowozin (Max Planck Institute for Biological Cybernetics, Tuebingen, Germany), Christoph Lampert (Max Planck Institute for Biological Cybernetics, Tuebingen, Germany)
Using Closed Captions to Train Activity Recognizers that Improve Video Retrieval
Authors:
Sonal Gupta (University of Texas at Austin), Raymond Mooney (University of Texas at Austin)
Event Detection Using Local Binary Pattern Based Dynamic Textures
Authors:
Yunqian Ma (Honeywell Labs), Petr Cisar
Nonparametric Bottom-Up Saliency Detection by Self-Resemblance
Authors:
HAE JONG SEO (UC, Santa Cruz), Peyman Milanfar (UC Santa Cruz)
Categorization in Natural Time-Varying Image Sequences
Authors:
Teresa Ko (UCLA), Stefano Soatto (UCLA), Deborah Estrin (UCLA)
Content and Context-Based Multi-Label Image Annotation
Authors:
Hong Lu (Fudan University), Yingbin Zheng (Fudan University), Xiangyang Xue (Fudan University), Yuejie Zhang (Fudan University)
Estimating Object Region from Local Contour Configuration
Authors:
Tetsuaki Suzuki (NEC Corporation), Martial Hebert (CMU)
Head and Gaze Dynamics in Visual Attention and Context Learning
Authors:
Anup Doshi (UCSD), Mohan Trivedi (UCSD)
Efficient Acquisition of Human Existence Priors from Motion Trajectories
Authors:
Hitoshi Habe (NAIST), Hidehito Nakagawa (NAIST), Masatsugu Kidode (NAIST)
Scenes vs. Objects: a Comparative Study of Two Approaches to Context Based Recognition
Authors:
Andrew Rabinovich (Google), Serge Belongie (UCSD)
Towards Total Scene Understanding: Classification, Annotation and Segmentation in an Automatic Framework
Authors:
Li-Jia Li (Princeton), Richard Socher (Princeton University), Li Fei-Fei (Princeton University)
Mining Discriminative Adjectives and Prepositions for Natural Scene Recognition
Authors:
Bangpeng Yao (Princeton University), Juan Carlos Niebles (Princeton University), Li Fei-Fei (Princeton University)
Hierarchical Audio-Visual Cue Integration Framework for Activity Analysis in Intelligent Meeting Rooms
Authors:
Shankar Shivappa (University of California, SD), Mohan Trivedi (UCSD), Bhaskar Rao (University of California, SD)
ViSU'09 - Introduction
ViSU'09 - Panel 1
ViSU'09 - Keynote
ViSU'09 - Panel 2
ViSU'09 - Panel 3
VCL-ViSU Joint Award and Final Remarks