Showing 2024Show all
2 papers · 1 filter
cs.CV2024
CigTime: Corrective Instruction Generation Through Inverse Motion Editing
Qihang Fang, Chengcheng Tang, Bugra Tekin +1
Recent advancements in models linking natural language with human motions have shown significant promise in motion generation and editing based on instructional text. Motivated by…
cs.CV2024
BID: Boundary-Interior Decoding for Unsupervised Temporal Action Localization Pre-Trainin
Qihang Fang, Chengcheng Tang, Shugao Ma +1
Skeleton-based motion representations are robust for action localization and understanding for their invariance to perspective, lighting, and occlusion, compared with images. Yet,…