Action Recognition On Charades Ego
평가 지표
mAP
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | mAP | Paper Title | Repository |
|---|---|---|---|
| HierVL | 33.8 | HierVL: Learning Hierarchical Video-Language Embeddings | |
| EgoVLP | 32.1 | Egocentric Video-Language Pretraining | |
| LaViLa (Zero-shot, TimeSformer-L) | 28.9 | Learning Video Representations from Large Language Models | |
| LaViLa (Finetuned, TimeSformer-L) | 36.1 | Learning Video Representations from Large Language Models | |
| EgoVLPv2 | 34.1 | EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone | |
| HierVL (Zero-shot) | 26 | HierVL: Learning Hierarchical Video-Language Embeddings |
0 of 6 row(s) selected.