6 papers
Action Motifs: Self-Supervised Hierarchical Representation of Human Body Movements
Genki Kinoshita, Shu Nakamura, Ryo Kawahara +3
Effective human behavior modeling requires a representation of the human body movement that capitalizes on its compositionality. We propose a hierarchical representation consisting…
REACH: Hand Pose Estimation from Room Corners
Shu Nakamura, Ryo Kawahara, Genki Kinoshita +4
We introduce a novel 3D hand pose estimator that can accurately recover the shape and pose of people's hands in a room from afar, typically from fixed cameras at room corners, in e…
SteerPose: Simultaneous Extrinsic Camera Calibration and Matching from Articulation
Sang-Eun Lee, Ko Nishino, Shohei Nobuhara
Can freely moving humans or animals themselves serve as calibration targets for multi-camera systems while simultaneously estimating their correspondences across views? We humans c…
Spatiotemporal Multi-Camera Calibration using Freely Moving People
Sang-Eun Lee, Ko Nishino, Shohei Nobuhara
We propose a novel method for spatiotemporal multi-camera calibration using freely moving people in multiview videos. Since calibrating multiple cameras and finding matches across…
RatBodyFormer: Rat Body Surface from Keypoints
Ayaka Higami, Karin Oshima, Tomoyo Isoguchi Shiramatsu +3
Analyzing rat behavior lies at the heart of many scientific studies. Past methods for automated rodent modeling have focused on 3D pose estimation from keypoints, e.g., face and ap…
Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment
Hiromu Taketsugu, Takeru Oba, Takahiro Maeda +2
Humans can predict future human trajectories even from momentary observations by using human pose-related cues. However, previous Human Trajectory Prediction (HTP) methods leverage…