A dataset with fully annotated attention targets in video for attention target estimation.
Variants: VideoAttentionTarget
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Gaze Target Estimation | ViTGaze | ViTGaze: Gaze Following with Interaction … | 2024-03-19 |
Recent papers with results on this dataset: