SSRL: Self-Supervised Spatial-Temporal Representation Learning for 3D Action Recognition.
Zhihao JinYifan WangQicong WangYehu ShenHongying MengPublished in: IEEE Trans. Circuits Syst. Video Technol. (2024)
Keyphrases
- spatial temporal
- action recognition
- human actions
- recognizing human actions
- action recognition in videos
- recognition of human actions
- spatio temporal
- bag of words
- activity recognition
- view invariant
- temporal information
- spatial and temporal
- bag of features
- active learning
- information retrieval
- video database
- video shots