Tentative Schedule
The workshop will be held on 9 September 2026.
08:40 – 08:50 Welcome and opening remarks
08:50 – 09:15 Invited Talk #1: Zhengyi Luo : Is Motion Tracking All You Need? Scaling Humanoid Control from Simulation to the Real World
09:15 – 09:40 Invited Talk #2: Kwan-Yee Lin: Toward Evolving Humanoid Motion Intelligence: Inward to the Body, Outward to the World
09:40 – 10:20 Invited Talk #3: Taku Komura: Capturing Human Scene Interaction Data with Handheld Devices
10:20 – 10:40 Paper Talks
RePointer: Retrieval-Anchored Candidate Generation and Detector-Robust Selection for Referential Gestures
Yuan He, Rachel McDonnell
Recovering Humans in Context: Joint 4D Scene and Human Body Reconstruction from Monocular Video
Dror Moran, Uri Patish, Itai Druker, Wojciech Zielonka, Egor Zakharov
10:40 - 11:10 Break + Poster
RePointer: Retrieval-Anchored Candidate Generation and Detector-Robust Selection for Referential Gestures
Yuan He, Rachel McDonnell
Recovering Humans in Context: Joint 4D Scene and Human Body Reconstruction from Monocular Video
Dror Moran, Uri Patish, Itai Druker, Wojciech Zielonka, Egor Zakharov
TCR: Temporal Compression and Recovery for Efficient Video-Based 3D Human Pose Estimation
Shuo Yang, Hichem Sahli, Xuan Son Nguyen, Aymeric Histace, Bart Jansen
PASI: Panoramic Adaptive Sliced Inference for Open-Vocabulary Instance Segmentation in Equirectangular Panoramas
Teodor Kirilov, Junwei Zheng, Ruiping Liu, Yufan Chen, Di Wen, Jiale Wei, Kunyu Peng, Kailun Yang, Jiaming Zhang, Rainer Stiefelhagen
Seeing My Future: Predicting Situated Interaction Behavior in Virtual Reality
Yuan Xu, Zimu Zhang, Xiaoxuan Ma, Wentao Zhu, Yu QIAO, Yizhou Wang
GRAFT: Geometric Refinement and Fitting Transformer for Human Scene Reconstruction
Pradyumna YM, Yuxuan Xue, Yue Chen, Nikita Kister, István Sárándi, Gerard Pons-Moll
GESTO: Human-Centric Spatio-Temporal Memory for Reasoning in Dynamic Scenes
Ermanno Bartoli, Buwei He, Dennis Rotondi, Sebastian Koch, Federico Tombari, Kai O. Arras, Patric Jensfelt, Yixi Cai, Iolanda Leite
MIBURI: Towards Expressive Interactive Gesture Synthesis
M. Hamza Mughal, Rishabh Dabral, Vera Demberg, Christian Theobalt
11:10 – 11:50 Invited Talk #4: Gerard Pons-Moll: INTERACT: Reconstructing, Generating and Grounding Humans in 3D Worlds
11:50 – 12:30 Invited Talk #5: Umar Iqbal: Generating Human(oid)-Scene Interactions via Video Priors
12:30 – 12:35 Closing Remarks