9 papers
High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation
Runyang Feng, Hyung Jin Chang, Tze Ho Elden Tse +3
Modeling high-resolution spatiotemporal representations, including both global dynamic contexts (e.g., holistic human motion tendencies) and local motion details (e.g., high-freque…
Leveraging RGB Images for Pre-Training of Event-Based Hand Pose Estimation
Ruicong Liu, Takehiko Ohkawa, Tze Ho Elden Tse +3
This paper presents RPEP, the first pre-training method for event-based 3D hand pose estimation using labeled RGB images and unpaired, unlabeled event data. Event data offer signif…
Improving Human Motion Plausibility with Body Momentum
Ha Linh Nguyen, Tze Ho Elden Tse, Angela Yao
Many studies decompose human motion into local motion in a frame attached to the root joint and global motion of the root joint in the world frame, treating them separately. Howeve…
TIGeR: Text-Instructed Generation and Refinement for Template-Free Hand-Object Interaction
Yiyao Huang, Zhedong Zheng, Yu Ziwei +3
Pre-defined 3D object templates are widely used in 3D reconstruction of hand-object interactions. However, they often require substantial manual efforts to capture or source, and i…
Visual Intention Grounding for Egocentric Assistants
Pengzhan Sun, Junbin Xiao, Tze Ho Elden Tse +3
Visual grounding associates textual descriptions with objects in an image. Conventional methods target third-person image inputs and named object queries. In applications such as A…
A Constrained Optimization Approach for Gaussian Splatting from Coarsely-posed Images and Noisy Lidar Point Clouds
Jizong Peng, Tze Ho Elden Tse, Kai Xu +2
3D Gaussian Splatting (3DGS) is a powerful reconstruction technique, but it needs to be initialized from accurate camera poses and high-fidelity point clouds. Typically, the initia…