Tuesday, June 23

Time: 10:30—12:30
Location: Splash 9-16

• Cooperative Mapping of Multiple PTZ Cameras in Automated Surveillance Systems (Chung-Hao Chen (The University of Tennessee, Knoxville), Yi Yao (GE Global Research Center), Anis Drira (The University of Tennessee, Knoxville), Andreas Koschan (The University of Tennessee, Knoxville), Mongi Abidi (The University of Tennessee, Knoxville))
• Tour the World: building a web-scale landmark recognition engine (Yan-Tao Zheng (National University of Singapore), Ming Zhao (Google Inc.), Yang Song (Google Inc.), Hartwig Adam (Google Inc.), Ulrich Buddemeier (Google Inc.), Alessandro Bissacco (Google Inc.), Fernando Brucher (Google Inc.), Tat-Seng Chua (National University of Singapore), Hartmut Neven (Google Inc.))

• Flow Mosaicking: Real-time Pedestrian Counting without Scene-specific Learning (Yang Cong (Chinese Academy of Sciences), Haifeng Gong (UCLA), Song-Chun Zhu (UCLA & Lotus Hill Institute), Yandong Tang (Chinese Academy of Sciences))
• VideoTrek: A Vision System for a Tag-along Robot (Oleg Naroditsky (Sarnoff Corporation), Zhiwei Zhu (Sarnoff Corporation), Aveek Das (Sarnoff Corporation), Supun Samarasekera (Sarnoff Corporation), Taragay Oskiper (Sarnoff Corporation), Rakesh Kumar (Sarnoff Corporation))
• A Projector-based Movable Hand-held Display System (Man Chuen Leung (The Chinese University of Hong Kong), Kai Ki Lee (The Chinese University of Hong Kong), Kin Hong Wong (The Chinese University of Hong Kong), Michael Ming Yuen Chang (The Chinese University of Hong Kong))

• Facial Deblur Inference to Improve Recognition of Blurred Faces (Masashi Nishiyama (Toshiba), Hidenori Takeshima (Toshiba), Tatsuo Kozakaya (Toshiba), Jamie Shotton (Microsoft Research Cambridge), Osamu Yamaguchi (Toshiba))
• Coupled Spectral Regression for Matching Heterogeneous Faces (Zhen Lei (Chinese Academy of Sciences), Stan Li (Chinese Academy of Sciences))
• Efficiently training a better visual detector with sparse Eigenvectors (Sakrapee Paisitkriangkrai (NICTA), Chunhua Shen (NICTA), Jian Zhang (NICTA))
• Observable Subspaces for 3D Human Motion Recovery (Andrea Fossati (EPFL), Mathieu Salzmann (University of California, Berkeley), Pascal Fua (EPFL))

• “Who are you?” - Learning person specific classifiers from video (Josef Sivic (INRIA & Ecole Normale Superieure), Mark Everingham (University of Leeds), Andrew Zisserman (University of Oxford))
• A Revisit of Generative Model for Automatic Image Annotation using Markov Random Fields (Yu Xiang (Fudan University), Xiangdong Zhou (Fudan University), Tat-Seng Chua (National University of Singapore), Chong-Wah Ngo (City University of Hong Kong))
• Vocabulary Hierarchy Optimization for Effective and Transferable Retrieval (Rongrong Ji (Harbin Institute of Technology), Xing Xie (Microsoft Research Asia), Hongxun Yao (Harbin Institute of Technology), Wei-Ying Ma (Microsoft Research Asia))

• On the burstiness of visual elements (Herve Jegou (INRIA), Matthijs Douze (INRIA), Cordelia Schmid (INRIA))
• Distance Transform Templates for Object Detection and Pose Estimation (Stefan Holzer (TU Munich), Stefan Hinterstoisser (TU Munich), Slobodan Ilic (Deutsche Telekom Labs & TU Berlin), Nassir Navab (TU Munich))

• Isometric Registration of Ambiguous and Partial Data (Art Tevs (Max Planck Institute Informatik), Martin Bokeloh (University of TŸbingen), Michael Wand (Saarland University & Max Planck Institut Informatik), Andreas Schilling (WSI/GRIS, University of Tuebingen), Hans-Peter Seidel (Max Planck Institut Informatik))

• Convexity and Bayesian Constrained Local Models (Ulrich Paquet (Imense Ltd))
• Multi-Object Tracking through Occlusions by Local Tracklets Filtering and Global Tracklets Association with Detection Responses (Junliang Xing (Tsinghua University), Haizhou Ai (Tsinghua University), Shihong Lao (Omron Corporation))

• Tracking of a Non-Rigid Object via Patch-based Dynamic Appearance Modeling and Adaptive Basin Hopping Monte Carlo Sampling (Joonsuk Kwon (Seoul National University), Kyoung Mu Lee (Seoul National University))

• Projective Least-Squares: Global Solutions with Local Optimization (Carl Olsson (Lund University), Fredrik Kahl (Lund University), Richard Hartley (Australian National University & NICTA))
• A minimal parameterization of the trifocal tensor (Klas Nordberg (Linkšping University))
• Visibility Constraints on Features of 3D Objects (Ronen Basri (Weizmann Institute of Science), Pedro Felzenszwalb (University of Chicago), Ross Girshick (University of Chicago), David Jacobs (University of Maryland), Caroline Klivans (University of Chicago))
• Keypoint Induced Distance Profiles for Visual Recognition (Tat-Jun Chin (The University of Adelaide), David Suter (The University of Adelaide))
• A Multi-View Probabilistic Model for 3D Object Classes (Min Sun (Princeton University), Hao Su (Princeton University), Silvio Savarese (University of Michigan), Li Fei-Fei (Princeton University))
• Granularity-tunable Gradients Partition (GGP) Descriptors for Human Detection (Yazhou Liu (Harbin Institute of Technology), Shiguang Shan (Chinese Academy of Sciences), Wenchao Zhang (Chinese Academy of Sciences), Xilin Chen (Chinese Academy of Sciences), Wen Gao (Chinese Academy of Sciences))
• Unsupervised Feature Optimization (UFO): simultaneous selection of multiple features with their detection parameters (Leonid Karlinsky (Weizmann Institute of Science), Michael Dinerstein (Weizmann Institute of Science), Shimon Ullman (Weizmann Institute of Science))

• An Empirical Study of Context in Object Detection (Santosh Kumar Divvala (Robotics Institute, Carnegie Mellon University), Derek Hoiem (University of Illinois at Urbana-Champaign), James Hays (Carnegie Mellon University), Alexei Efros (Carnegie Mellon University), Martial Hebert (Carnegie Mellon University))
• Appearance-based Keypoint Clustering (Francisco Estrada (University of Toronto at Scarborough), Pascal Fua (EPFL), Vincent Lepetit (EPFL), Sabine SŸsstrunk (EPFL))

• Robust Unsupervised Segmentation of Degraded Document Images with Topic Models (Timothy Burns (University at Buffalo), Jason Corso (SUNY at Buffalo))
• Shape Priors and Discrete MRFs for Knowledge-based Segmentation (Ahmed Besbes (Ecole Centrale Paris), Nikos Komodakis (University of Crete), Georg Langs (CIR, Medical University of Vienna), Nikos Paragios (Ecole Centrale de Paris/INRIA Saclay, Ile-de-France))
• P-Brush: Continuous Valued MRFs with Normed Pairwise Distributions for Image Segmentation (Dheeraj Singaraju (Johns Hopkins University), Leo Grady (Siemens Corporate Research), Rene Vidal (Johns Hopkins University))
• Predicting High Resolution Image Edges with a Generic, Adaptive, 3-D Vehicle Model (Matthew Leotta (Brown University), Joseph Mundy (Brown University))
• Nonrigid Shape Recovery by Gaussian Process Regression (Jianke Zhu (ETH Zurich), Steven C.H. Hoi (Nanyang Technological University), Michael Lyu (The Chinese University of Hong Kong))

• 3D Morphable Face Models Revisited (Ankur Patel (University of York), William Smith (University of York))
• Shape Band: A Deformable Object Detection Approach (Xiang Bai (Huazhong University of Science and Technology), Quannan Li (Huazhong University of Science and Technology), Longin Jan Latecki (Temple University), Wenyu Liu (Huazhong University of Science and Technology), Zhuowen Tu (UCLA))
• Robust Object Detection Using Marginal Space Learning and Ranking-Based Multi-Detector Aggregation: Application to Left Ventricle Detection in 2D MRI Images (Yefeng Zheng (Siemens Corporate Research), Xiaoguang Lu (Siemens Corporate Research), Bogdan Georgescu (Siemens Corporate Research), Arne Littmann (Siemens Healthcare Sector), Edgar Mueller (Siemens Healthcare Sector), Comaniciu Dorin (Siemens Corporate Research))
• Layered Graph Matching by Composite Cluster Sampling with Collaborative and Competitive Interactions (Liang Lin (UCLA), Kun Zeng (Lotus Hill Institute), Xiaobai Liu (Huazhong University of Science and Technology & Lotus Hill Institute), Song-Chun Zhu (UCLA & Lotus Hill Institute))
• A Min-Max Framework of Cascaded Classifier with Multiple Instance Learning for Computer Aided Diagnosis (Dijia Wu (Rensselaer Polytechnic Institute), Jinbo Bi (Siemens Medical Solutions), Kim Boyer (Rensselaer Polytechnic Institute))
• Building text features for object image classification (Gang Wang (University of Illinois at Urbana-Champaign), Derek Hoiem (University of Illinois at Urbana-Champaign), David Forsyth (University of Illinois at Urbana-Champaign))
• Domain Transfer SVM for Video Concept Detection (Lixin Duan (Nanyang Technological University), Ivor Wai-Hung TSANG (Nanyang Technological University), Dong Xu (Nanyang Technological University), Stephen Maybank (University of London))
• Minimizing Sparse Higher Order Energy Functions of Discrete Variables (Carsten Rother (Microsoft Research Cambridge), Pushmeet Kohli (Microsoft Research Cambridge), Wei Feng (The Chinese University of Hong Kong), Jiaya Jia (The Chinese University of Hong Kong))
• Label Diagnosis through Self Tuning for Web Image Search (Jun Wang (Columbia University), Yu-Gang Jiang (Columbia University), Shih-fu Chang (Columbia University))
• Learning IMED via Translation Invariant Transformation (Bing Sun (Key Laboratory of Machine Perception (MOE), School of EECS, Peking University), Jufu Feng (Peking University), Liwei Wang (Peking University))
• Markov Chain Monte Carlo Combined with Deterministic Methods for Markov Random Field Optimization (Wonsik Kim (Seoul National University), Kyoung Mu Lee (Seoul National University))
• Stereographic Rectification of Omnidirectional Stereo Pairs (Jan Heller (Czech Technical University), Tomas Pajdla (Czech Technical University))
• Manhattan-world Stereo (Yasutaka Furukawa (University of Washington), Steve Seitz (University of Washington), Brian Curless (University of Washington), Richard Szeliski (Microsoft Research))

• Towards high-resolution large-scale multi-view stereo (Vu Hoang Hiep (Certis ENPC), Renaud Keriven (Ecole des Ponts ParisTech), Jean-Philippe Pons (CSTB), Patrick Labatut (CERTIS))
• Visual loop closure detection using multi-resolution SIFT grids in metric-topological SLAM (Vivek Pradeep (University of Southern California), Gerard Medioni (University of Southern California), James Weiland (University of Southern California))

• Anomaly Detection in Extremely Crowded Scenes using Spatio-Temporal Motion Pattern Models (Louis Kratz (Drexel University), Ko Nishino (Drexel University))
• Dense saliency-based spatiotemporal feature points for action recognition (Konstantinos Rapantzikos (National Technical University of Athens), Yannis Avrithis (National Technical University of Athens), Stefanos Kollias (National Technical University of Athens))

• Monitoring, Recognizing and Discovering Social Networks (Ting Yu (GE Global Research), Ser Nam Lim (GE Global Research), Kedar Patwardhan (GE Global Research), Nils Krahnstoever (GE Global Research))
• Recognizing Human Group Activities by Localized Causalities (Bingbing Ni (National University of Singapore), Shuicheng Yan (National University of Singapore), Ashraf Kassim (National University of Singapore))
• Human Motion Synthesis from 3D Video (Peng Huang (University of Surrey), Adrian Hilton (University of Surrey), Jonathan Starck (The Foundry))

• Distributed Multi-Target Tracking In A Self-Configuring Camera Network (Cristian Soto (University of California, Riverside), Bi Song (University of California, Riverside), Amit Roy-Chowdhury (University of California, Riverside))

• Active Stereo Tracking of Multiple Free-Moving Targets (Luis Perdigoto (University of Coimbra), Joao Barreto (University of Coimbra), Rui Caseiro (University of Coimbra), Helder Araujo (University of Coimbra))

This entry was posted on Friday, May 1st, 2009 at 11:15 am and is filed under Uncategorized. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.