| Paper | Code | mAP | ModelName | ReleaseDate |
|---|---|---|---|---|
| Actor-agnostic Multi-label Action Recognition with Multi-modal Query | ✓ Link | 35.59 | MSQNet | 2023-07-20 |
| VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners | 25.8 | VideoCoCa | 2022-12-09 | |
| MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge | ✓ Link | 23.8 | MAXI | 2023-03-15 |
| A CLIP-Hitchhiker's Guide to Long Video Retrieval | ✓ Link | 21.1 | CLIP-Hitchhiker (ViT-B/16, 32 frames) | 2022-05-17 |