Each paper presentation will be 15 minutes (10 minutes oral presentation + 5 minutes questions & discussion).
Time Talk 09:00 - 09:15 Welcome and Opening Remarks 09:15 - 10:00 Invited Talk: Understanding and shaping the athlete’s brain using body-mind reading and feedback. Makio Kashino, Head of Sports Brain Science Project @ NTT Communication Science Laboratories. 10:15 - 10:30 A Convolutional Sequence to Sequence Model for Multimodal Dynamics Prediction in Ski Jumps. Dan Zecha, Christian Eggert, Moritz Einfalt, Stephan Brehm, Rainer Lienhart. 10:30 - 11:00 Coffee Break 11:00 - 11:15 Stillness Moves: Exploring Body Weight-Transfer Learning in Physical Training for Tai-Chi Exercise. Han Hong, Ping Hsuan Han, Kuan Yin Lu, Chia Hung Sun, Pei Yi Lee, Amy Ming Sui Lee, Wei Zen Sun, Yi-Ping Hung. 11:30 - 11:45 An On-site Visual Feedback Method Using Bullet-Time Video. Takasuke Nagai, Hidehiko Shishido, Yoshinari Kameda, Itaru Kitahara. 11:45 - 12:00 Using Virtual Reality and Head-Mounted Displays to Increase Performance in Rowing Workouts. Sebastian Arndt, Andrew Perkis, Jan-Niklas Voigt-Antons. 12:00 - 12:15 ORSNet: A Hybrid Neural Network for Official Sports Referee Signal Recognition. Tse-Yu Pan, Chen-Yuan Chang, Wan-Lun Tsai, Min-Chun Hu. 12:15 - 12:30 Development of a Virtual Environment for Motion Analysis of Tennis Service Returns. Kei Saito, Katsutoshi Masai, Yuta Sugiura, Toshitaka Kimura, Maki Sugimoto. 12:30 - 12:45 Swimming Pool Occupancy Analysis using Deep Learning on Low Quality Video. Morten B. Jensen, Rikke Gade, Thomas B. Moeslund. 12:45 - 14:00 Lunch 14:00 - 14:45 Invited Talk: Practical sports video analysis at Qoncept: a few case studies. Tuukka Karvonen, Qoncept Inc. 14:45 - 15:00 Sports Video Captioning by Attentive Motion Representation based Hierarchical Recurrent Neural Networks. Mengshi Qi, Yunhong Wang, Annan Li, Jiebo Luo. 15:00 - 15:15 Estimation of Runners' Number of Steps, Stride Length and Speed Transition from Video of a 100-Meter Race. Kentaro Yagi, Kunihiro Hasegawa, Yuta Sugiura, Hideo Saito. 15:15 - 15:30 Fast and Accurate Object Detection Using Image Cropping/Resizing in Multi-View 4K Sports Videos. Jianfeng Xu, Kanokphan Lertniphonphan, Kazuyuki Tasaka. 15:30 - 15:35 Closing Remarks
Makio Kashino received his B.A., M.A., and Ph.D. in psychophysics from the University of Tokyo in 1987, 1989, and 2000. He joined NTT as a researcher in 1989. Currently, he is an NTT Fellow / Director of Sports Brain Science Project, NTT Communication Science Laboratories, and a Specially-Appointed Professor in the School of Engineering, Tokyo Institute of Technology. Using an interdisciplinary research approach bridging cognitive neuroscience and information and communication technology, Dr. Kashino has been studying the functional and neural mechanisms of human cognition, especially auditory perception, cross-modal and sensorimotor interaction, and interpersonal communication, not only in typical people, but also in people with autism spectrum disorder and elite athletes.
Tuukka Karvonen obtained his Ph.D. from Kyoto University, and is currently Chief Researcher at Qoncept, Inc., a VC company launched from Osaka University in 2008 that focuses on realtime computer vision solutions for scenarios such as markerless AR, recognition and tracking for sports, and VSLAM for autonomous robot movement. Tuukka’s research is in computer vision and machine learning, and current research interests include human pose estimation, human motion analysis and action recognition. He is also interested in solving the practical issues of applying such technologies in the field.