Workshop 2013 challenge

The 2013 Multi-modal Challenge workshop will be held on Dec. 9th in the Level 3 Seminar Room of the NICTA Australian Techonology Park Laboratory, Redferm, in conjunction with ICMI 2013, will be devoted to the presentation of most recent and challenging techniques from multi-modal gesture recognition. The program is detailed next:

9:00h    Opening: Presentation of the workshop


9:15h   Invited speaker I: Leonid Sigal, Disney Research
             Title: Action Recognition and Understanding: Latest Challenges and Opportunities 


10:00h Challenge results presentation
             Multi-modal Gesture Recognition Challenge 2013: Dataset and Results
             Sergio Escalera, Jordi Gonzàlez, Xavier Baró, Miguel Reyes, Oscar Lopes, Isabelle Guyon, Vassilis Athistos, Hugo J.Escalante


10:30h  Coffee break I 

11:00h Invited speaker II: Cristian Sminchisescu, Lund University
             Title: Human Actions and 3D Pose in the Eye: From Perceptual Evidence to Accurate Computational Models

11:45h Presentations I: Multi-modal Gesture Recognition Challenge I and award ceremony
             Fusing Multi-modal Features for Gesture Recognition (1st Prize)
             Jiaxiang Wu, Jian Cheng, Chaoyang Zhao and Hanqing Lu



             A Multi Modal Approach to Gesture Recognition from Audio and Video Data (3rd Prize)
             Immanuel Bayer, Thierry Silbermann

12:30h  Lunch break (included and sponsored by National ICT Australia)

13:30h Invited speaker III: Antonis Argyros, Univ. of Crete, Institute of Computer Science
             Title: Tracking the articulated motion of human hands


14:15h Presentations II: Multi-modal Gesture Recognition Challenge II
             Online RGB-D Gesture Recognition with Extreme Learning Machines
             Xi Chen and Markus Koskela


             A Multi-modal Gesture Recognition System Using Audio, Video, and Skeletal Joint Data
             Karthik Nandakumar, Kong-Wah Wan, Jian-Gang Wang, Wen Zheng Terence Ng, Siu Man Alice Chan and Wei-Yun Yau

15:15h Invited speaker IV: Richard Bowden, University of Surrey
             Title: Recognising spatio-temporal events in video


16:00h  Coffee break II

16:30h Presentations III: Challenge for Multimodal Mid-Air Gesture Recognition for close HCI
             ChAirGest - A Challenge for Multimodal Mid-Air Gesture Recognition for close HCI
             Simon Ruffieux, Denis Lalanne and Elena Mugellini


             ChAirGest - Gesture Spotting and Recognition Using Saliency Detection and Concatenated HMMs
             Ying Yin and Randall Davis


17:30h Presentations IV: Multimodal Gesture Recognition Applications
             Multi-modal Social Signal Analysis for Predicting Agreement in Conversation Settings
             Víctor Ponce-López, Sergio Escalera, and Xavier Baró


             Multi-modal Descriptors for Multi-class Hand Pose Recognition in Human Computer Interaction Systems
             Jordi Abella, Raúl Alcaide, Anna Sabaté, Joan Mas, Sergio Escalera, Jordi Gonzàlez, Coen Antens

18:15h Closing: Conclusions the workshop