Spatial & temporal attention combines the advantages of spatial attention and temporal attention as it adaptively selects both important regions and key frames. Some works compute temporal attention and spatial attention separately, while others produce joint spatio & temporal attention maps. Further works focusing on capturing pairwise relations.
Source: An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton DataPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Action Recognition | 2 | 18.18% |
Semantic Segmentation | 1 | 9.09% |
Cross-Modal Retrieval | 1 | 9.09% |
Explainable Models | 1 | 9.09% |
Retrieval | 1 | 9.09% |
Text to Video Retrieval | 1 | 9.09% |
Video-Text Retrieval | 1 | 9.09% |
Visual Reasoning | 1 | 9.09% |
Skeleton Based Action Recognition | 1 | 9.09% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |