| Paper | Code | mAP | ModelName | ReleaseDate |
|---|---|---|---|---|
| Learning Video Representations from Large Language Models | ✓ Link | 36.1 | LaViLa (Finetuned, TimeSformer-L) | 2022-12-08 |
| EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone | ✓ Link | 34.1 | EgoVLPv2 | 2023-07-11 |
| HierVL: Learning Hierarchical Video-Language Embeddings | ✓ Link | 33.8 | HierVL | 2023-01-05 |
| Egocentric Video-Language Pretraining | ✓ Link | 32.1 | EgoVLP | 2022-06-03 |
| Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos | 30.13 | Ego-Exo*-R101 | 2021-04-16 | |
| Learning Video Representations from Large Language Models | ✓ Link | 28.9 | LaViLa (Zero-shot, TimeSformer-L) | 2022-12-08 |
| Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos | 28.2 | ResNet-152 (Charades-Ego supervised) | 2018-04-25 | |
| HierVL: Learning Hierarchical Video-Language Embeddings | ✓ Link | 26 | HierVL (Zero-shot) | 2023-01-05 |