3 papers
cs.CV2026
STAR: Skeletal Token Alignment and Rearrangement for Interaction Recognition
Yuhang Wen, Mengyuan Liu, Zixuan Tang +3
Understanding physical human-robot and human-human interactions is a challenging yet emerging topic in 3D vision. While most existing methods rely on skeleton sequences--effective…
cs.CV2025
Informative Sample Selection Model for Skeleton-based Action Recognition with Limited Training Samples
Zhigang Tu, Zhengbo Zhang, Jia Gong +2
Skeleton-based human action recognition aims to classify human skeletal sequences, which are spatiotemporal representations of actions, into predefined categories. To reduce the re…
cs.CV2025
FADE: A Dataset for Detecting Falling Objects around Buildings in Video
Zhigang Tu, Zhengbo Zhang, Zitao Gao +3
Objects falling from buildings, a frequently occurring event in daily life, can cause severe injuries to pedestrians due to the high impact force they exert. Surveillance cameras a…