📊 Showing 6 results | 📏 Metric: mAP
| Rank | Model | Paper | mAP | Date | Code |
|---|---|---|---|---|---|
| 1 | LaViLa (Finetuned, TimeSformer-L) | Learning Video Representations from Large Language Models | 36.10 | 2022-12-08 | 📦 facebookresearch/lavila 📦 Ziyang412/VideoTree 📦 ceezh/llovi |
| 2 | EgoVLPv2 | EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone | 34.10 | 2023-07-11 | 📦 facebookresearch/EgoVLPv2 |
| 3 | HierVL | HierVL: Learning Hierarchical Video-Language Embeddings | 33.80 | 2023-01-05 | 📦 facebookresearch/hiervl |
| 4 | EgoVLP | Egocentric Video-Language Pretraining | 32.10 | 2022-06-03 | 📦 showlab/egovlp 📦 zhaoyue-zephyrus/avion |
| 5 | LaViLa (Zero-shot, TimeSformer-L) | Learning Video Representations from Large Language Models | 28.90 | 2022-12-08 | 📦 facebookresearch/lavila 📦 Ziyang412/VideoTree 📦 ceezh/llovi |
| 6 | HierVL (Zero-shot) | HierVL: Learning Hierarchical Video-Language Embeddings | 26.00 | 2023-01-05 | 📦 facebookresearch/hiervl |