Search Results for author:
Found 3 papers, 0 papers with code
GaitFormer: Revisiting Intrinsic Periodicity for Gait Recognition
The second component is the Temporal Aggregation Module (TAM), which separates embeddings into trend and seasonal components, and extracts meaningful temporal correlations to identify primary components, while filtering out random noise.
Motion Sensitive Contrastive Learning for Self-supervised Video Representation
Contrastive learning has shown great potential in video representation learning.
Identity-aware Graph Memory Network for Action Detection
Action detection plays an important role in high-level video understanding and media interpretation.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
