Workshop 2014 challenge

The ChaLearn Looking at People Workshop 2014, to be held next September 6th and 7th in conjunction with ECCV 2014 at the Swiss Federal Institute of Technology (ETH) Zurich, will be devoted to the presentation of most recent and challenging techniques from human body pose recovery, action and gesture recognition.

The tentative program is described next:

Saturday 6th, September, 2014

09:00h Opening: Presentation of the workshop

09:15h Invited Speaker I: "4D Human Performance Capture", Adrian Hilton, Univ. Surrey

10:00h Session I: Challenge results presentation and award ceremony

W05-33 ChaLearn Looking at People Challenge 2014: Dataset and Results; Sergio Escalera, Xavier Baró, Jordi Gonzàlez, Miguel A. Bautista, Meysam Madadi, Miguel Reyes, Víctor Ponce, Hugo J. Escalante, Jamie Shotton, Isabelle Guyon; Spain, USA, Mexico, UK

10:30h Coffee Break

11:00h Session II: ChaLearn Track 3 - Winner methods

W05-07 Multi-scale deep learning for gesture detection and localization; Natalia Neverova, Christian Wolf, Graham W. Taylor and Florian Nebout; France, Canada

W05-29 A Multi-scale Boosted Detector for Efficient and Robust Gesture Recognition; Camille Monnier, Stan German and Andrey Ost; USA

W05-11 Nonparametric Gesture Labeling from Multi-modal Data; Ju Yong Chang; South Korea

12:00h Session III: ChaLearn Track 2 - Winner methods

W05-08 Action and Gesture Temporal Spotting with Super Vector Representation; Xiaojiang Peng, Limin Wang, Zhuowei Cai and Yu Qiao; China

W05-18 Mixture of Heterogeneous Attribute Analyzers for Human Action Detection; Yong Pei, Bingbing Ni and Indriyati Atmosukarto; Singapore

W05-16 Action Detection with Improved Dense Trajectories and Sliding Window; Zhixin Shu, Kiwon Yun and Dimitris Samaras; USA

13:00h Lunch break

14:00h Invited Speaker II: "Using linguistic modeling and linguistically annotated corpora for computer-based sign language recognition from video", Carol Neidle, Boston University

14:30h Session IV: ChaLearn Track 3

W05-14 Deep Dynamic Neural Networks for Gesture Segmentation and Recognition; Di Wu and Ling Shao; UK

W05-05 Sign Language Recognition Using Convolutional Neural Networks; Lionel Pigou, Sander Dieleman, Pieter-Jan Kindermans and Benjamin Schrauwen; Belgium

W05-25 Gesture Recognition using Template Based Random Forest Classifiers; Necati Cihan Camgöz, Ahmet Alp Kindiroglu and Lale Akarun; Turkey

15:30h Coffee Break

16:00h Invited Speaker III: Dimitris Metaxas, Rutgers

16:30h Session V: ChaLearn Track 3

W05-15 Continuous gesture recognition from articulated poses; Georgios D. Evangelidis, Gurkirt Singh and Radu Horaud; France, India

W05-20 Multi-modality Gesture Detection and Recognition With Un-supervision, Randomization and Discrimination; Guang Chen, Daniel Clarke, David Weikersdorfer, Manuel Giuliani, Andre Gaschler and Alois Knoll; Germany

W05-02 Multi-modal Gesture Recognition Using Skeletal Joints and Motion Trail Model; Bin Liang and Lihong Zheng; Australia

17:30h Closing

Sunday 7th, September, 2014

09:00h Opening

09:05h Invited Speaker IV: Fernando de la Torre, Carnegie Mellon

09:50h Session VI: Human Body Models

W05-19 Increasing 3D Resolution of Kinect Faces; Stefano Berretti, Pietro Pala and Alberto del Bimbo; Italy

W05-31 Subspace Procrustes Analysis; Xavier Perez-Sala, Fernando De la Torre, Laura Igual, Sergio Escalera and Cecilio Angulo; Spain, USA

10:30h Coffee Break

11:00h Invited Speaker V: "Intra- and Interpersonal Functions of Head Motion in Emotion Communication", Jeffrey Cohn, Pittsburgh Univ

12:00h Session VII: Human Poses and Parts

W05-06 Easy Minimax Estimation with Random Forests for Human Pose Estimation; P. Daphne Tsatsoulis and David Forsyth; USA

W05-32 Learning to Segment Humans by Stacking their Body Parts; Eloi Puertas, Miguel A. Bautista, Dani Sanchez, Sergio Escalera and Oriol Pujol; Spain

W05-03 G3Di: A Gaming Interaction Dataset and Real Time Interaction Evaluation Framework; Victoria Bloom, Vasileios Argyriou and Dimitrios Makris; UK

13:00h Lunch break

14:00h Invited Speaker VI: "3D Pose and Human Actions in the Eye: From Perceptual Evidence to Large-Scale Computational Models", Cristian Sminchisescu, Lund University

14:30h Session VIII: Multiple Cameras

W05-04 Three-Dimensional Hand Pointing Recognition using Two Cameras by Interpolation and Integration of Classification Scores; Dai Fujita and Takashi Komuro; Japan

W05-30 Video-based Action Detection using Multiple Wearable Cameras; Kang Zheng, Yuewei Lin, Youjie Zhou, Dhaval Salvi, Xiaochuan Fan, Dazhou Guo, Zibo Meng and Song Wang; USA

W05-34 Multiple Human Pose Estimation with Temporally Consistent 3D Pictorial Structures; Vasileios Belagiannis, Xinchao Wang, Bernt Schiele, Pascal Fua, Slobodan Ilic and Nassir Navab; Germany, Switzerland, USA

15:30h Coffee Break

16:00h Invited Speaker VII: "Recognising 3D Actions in the Wild", Richard Bowden, Univ. Surrey

16:30h Closing: Conclusions the workshop