3 papers
cs.CV2026
DiMoP: Diffusion-Driven Motion Representation Learning With Frame-Level Pseudo-Classification for Skeleton-Based Action Recognition
Shanaka Ramesh Gunasekara, Wanqing Li, Nikalal Kaldera +2
Robust skeleton-based action recognition requires representations that capture a wide spectrum of motions, from subtle to moderate and strong ones. Existing methods often focus on…
math.DS2025
Causal Discovery in Symmetric Dynamic Systems with Convergent Cross Mapping
Yiting Duan, Yi Guo, Jack Yang +1
This paper systematically discusses how the inherent properties of chaotic attractors influence the results of discovering causality from time series using convergent cross mapping…
cs.CV2024
Joint Temporal Pooling for Improving Skeleton-based Action Recognition
Shanaka Ramesh Gunasekara, Wanqing Li, Jack Yang +1
In skeleton-based human action recognition, temporal pooling is a critical step for capturing spatiotemporal relationship of joint dynamics. Conventional pooling methods overlook t…