| Home | Registration | Program |
| 09:00–09:05 | Opening Remarks |
| 09:05–09:35 | Invited Talk 1 |
| Yoichi Sato / The University of Tokyo (Japan) | |
| 09:35–10:05 | Invited Talk 2 |
| Angela Yao / National University of Singapore (Singapore) | |
| 10:05–10:15 | Coffee Break |
| 10:15–11:30 | Oral Session 1 |
| ・PocketSTPose: Causal Spatiotemporal Refinement for Mobile Sequential 3D HumanPose Estimation Yuto Nakamizo, Rintaro Kimura, Keiji Yanai |
|
| ・RallySpot: Joint Hit Detection and Stroke Recognition with Mitigated Detection Errors in Badminton Anam Shahzadi, Yuki Fujimura, Kazuya Kitano, Takuya Funatomi, Yasuhiro Mukaigawa |
|
| ・Analyzing Skeletal Feature Contributions for Signer Identification Manabu Okawa |
|
| ・Anomaly-Driven Semantic Mapping and VLM-Guided Active Investigation for Robotic Patrol Inspection Yusuke Yamashina, Naoki Higashi, Yoshihiko Ichikawa, Akito Mori |
|
| ・RECAL-Bench: A Unified Benchmark for REalistic, Context Aware Listener's Reaction Generation Lownish Rai Sookha (IIT Ropar), Shreya Ghosh (IIT Kharagpur), Mudasir Ganaie (IIT Ropar), Abhinav Dhall (Monash) |
|
| ・LingoMotion: An Interpretable and Unambiguous Symbolic Representation for Human Motion Yao Zhang, Zhuchenyang Liu, Yu Xiao |
|
| ・ADIScene: Affordance-Guided Diffusion for Interaction-Feasible 3D Scene Generation Misong Kim, JuYeong Hwang, SeungJeh Chung, Jaeyoung Seon, Ri Yu, HyeongYeop Kang |
|
| ・Improving Skeleton Representations for Anticipation through Feature-Space Self-Supervised Pre-Training Raphaël Lorenzo Louis, Serena Ivaldi, Bertrand Luvison |
|
| ・Streaming Video Instruction Tuning Jiaer Xia, Peixian Chen, Mengdan Zhang, Xing Sun, Kaiyang Zhou |
|
| 11:30–12:00 | Invited Talk 3 |
| Kent Fujiwara / LINE Yahoo (Japan) | |
| 12:00–13:30 | Lunch Break |
| 13:30–14:00 | Invited Talk 4 |
| Gim Hee Lee / National University of Singapore (Singapore) | |
| 14:00–14:30 | Invited Talk 5 |
| Matthew Walter / Toyota Technological Institute at Chicago (USA) | |
| 14:30–14:40 | Coffee Break |
| 14:40–16:00 | Oral Session 2 |
| ・Coordinates, Not Candidates: Dissecting Detector Ensembling for Dense-Crowd Tracking Doohyun Kim, Yonghoon Lee, Cho Chaeyeon, Sanghyun Kim |
|
| ・A Preliminary Study on Optical and Acoustic Time-of-Flight Sensing for Chopstick Grip Measurement Nanami Hirokawa, Yuki Choji, Kazuya Kitano, Yuki Fujimura, Takuya Funatomi, Yasuhiro Mukaigawa |
|
| ・Take or Put? Evaluating Wrist and Video Evidence for Retail Interaction Recognition Ichiro Tateyama, Matus Tanonwong, Koichi Hashimoto |
|
| ・HybridHOT: Learning Human-Centric Priors for Fine-Grained Human-Object Contact Segmentation Qihui Chen, Junwen Chen, Keiji Yanai |
|
| ・Learning Human Sports Motion Feasibility via Quantile Regression on Tracking Data Marc Gutiérrez-Pérez, Antonio Agudo |
|
| ・LHM-Humanoid: Long-Horizon Human Motion Control for Continuous Object Transport in Cluttered Scenes Haozhuo Zhang, Jingkai Sun, Michele Caprio, Angelo Cangelosi, Jian Tang, Shanghang Zhang, Qiang Zhang, Wei Pan |
|
| ・Hand-Object Contact Transition Detection in Egocentric Video Huy Anh Nguyen, Chang Dong, Feras Dayoub, Minh Hoai |
|
| ・Hexa-P: Physical Plausibility-aware Pre-training for Pedestrian Path Prediction Hiromu Taketsugu, Shohei Nobuhara, Norimichi Ukita |
|
| ・A Parameter-Efficient Conditional Path Model for Human Trajectory Prediction under Set Geometry Haeyun Seo |
|
| ・MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and Coaching Hao Yin, Paritosh Parmar, Lijun Gu, Lin Xu, Tianxiao Guo, Xiujin Liu, Tianyou Zheng, Yang Zhang, Weiwei Fu |
|
| 16:00–16:30 | Invited Talk 6 |
| Taku Komura / The University of Hong Kong (Hong Kong) | |
| 16:30–16:35 | Closing Remarks |
| ID | Paper title | Authors |
|---|---|---|
| 1 | PocketSTPose: Causal Spatiotemporal Refinement for Mobile Sequential 3D HumanPose Estimation | Yuto Nakamizo, Rintaro Kimura, Keiji Yanai |
| 3 | Anomaly-Driven Semantic Mapping and VLM-Guided Active Investigation for Robotic Patrol Inspection | Yusuke Yamashina, Naoki Higashi, Yoshihiko Ichikawa, Akito Mori |
| 4 | A Preliminary Study on Optical and Acoustic Time-of-Flight Sensing for Chopstick Grip Measurement | Nanami Hirokawa, Yuki Choji, Kazuya Kitano, Yuki Fujimura, Takuya Funatomi, Yasuhiro Mukaigawa |
| 6 | RallySpot: Joint Hit Detection and Stroke Recognition with Mitigated Detection Errors in Badminton | Anam Shahzadi, Yuki Fujimura, Kazuya Kitano, Takuya Funatomi, Yasuhiro Mukaigawa |
| 7 | Analyzing Skeletal Feature Contributions for Signer Identification | Manabu Okawa |
| 8 | Coordinates, Not Candidates: Dissecting Detector Ensembling for Dense-Crowd Tracking | Doohyun Kim, Yonghoon Lee, Cho Chaeyeon, Sanghyun Kim |
| 12 | Take or Put? Evaluating Wrist and Video Evidence for Retail Interaction Recognition | Ichiro Tateyama, Matus Tanonwong, Koichi Hashimoto |
| Paper title | Authors |
|---|---|
| HybridHOT: Learning Human-Centric Priors for Fine-Grained Human-Object Contact Segmentation | Qihui Chen, Junwen Chen, Keiji Yanai |
| RECAL-Bench: A Unified Benchmark for REalistic, Context Aware Listener's Reaction Generation | Lownish Rai Sookha, Shreya Ghosh, Mudasir Ganaie, Abhinav Dhall |
| LingoMotion: An Interpretable and Unambiguous Symbolic Representation for Human Motion | Yao Zhang, Zhuchenyang Liu, Yu Xiao |
| ADIScene: Affordance-Guided Diffusion for Interaction-Feasible 3D Scene Generation | Misong Kim, JuYeong Hwang, SeungJeh Chung, Jaeyoung Seon, Ri Yu, HyeongYeop Kang |
| Improving Skeleton Representations for Anticipation through Feature-Space Self-Supervised Pre-Training | Raphaël Lorenzo Louis, Serena Ivaldi, Bertrand Luvison |
| Learning Human Sports Motion Feasibility via Quantile Regression on Tracking Data | Marc Gutiérrez-Pérez, Antonio Agudo |
| LHM-Humanoid: Long-Horizon Human Motion Control for Continuous Object Transport in Cluttered Scenes | Haozhuo Zhang, Jingkai Sun, Michele Caprio, Angelo Cangelosi, Jian Tang, Shanghang Zhang, Qiang Zhang, Wei Pan |
| Hand-Object Contact Transition Detection in Egocentric Video | Huy Anh Nguyen, Chang Dong, Feras Dayoub, Minh Hoai |
| Hexa-P: Physical Plausibility-aware Pre-training for Pedestrian Path Prediction | Hiromu Taketsugu, Shohei Nobuhara, Norimichi Ukita |
| A Parameter-Efficient Conditional Path Model for Human Trajectory Prediction under Set Geometry | Haeyun Seo |
| Streaming Video Instruction Tuning | Jiaer Xia, Peixian Chen, Mengdan Zhang, Xing Sun, Kaiyang Zhou |
| MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and Coaching | Hao Yin, Paritosh Parmar, Lijun Gu, Lin Xu, Tianxiao Guo, Xiujin Liu, Tianyou Zheng, Yang Zhang, Weiwei Fu |