Contains 68,536 activity instances in 68.8 hours of first and third-person video, making it one of the largest and most diverse egocentric datasets available. Charades-Ego furthermore shares activity classes, scripts, and methodology with the Charades dataset, that consist of additional 82.3 hours of third-person video with 66,500 activity instances.
Source: Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos
Variants: Charades-Ego
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Action Recognition | EgoVLPv2 | EgoVLPv2: Egocentric Video-Language Pre-training with … | 2023-07-11 |
| Action Recognition | HierVL | HierVL: Learning Hierarchical Video-Language Embeddings | 2023-01-05 |
| Action Recognition | HierVL (Zero-shot) | HierVL: Learning Hierarchical Video-Language Embeddings | 2023-01-05 |
| Action Recognition | LaViLa (Finetuned, TimeSformer-L) | Learning Video Representations from Large … | 2022-12-08 |
| Action Recognition | LaViLa (Zero-shot, TimeSformer-L) | Learning Video Representations from Large … | 2022-12-08 |
| Action Recognition | EgoVLP | Egocentric Video-Language Pretraining | 2022-06-03 |
Recent papers with results on this dataset: