📊 Showing 4 results | 📏 Metric: mAP
| Rank | Model | Paper | mAP | Date | Code |
|---|---|---|---|---|---|
| 1 | MSQNet | Actor-agnostic Multi-label Action Recognition with Multi-modal Query | 35.59 | 2023-07-20 | 📦 mondalanindya/msqnet |
| 2 | VideoCoCa 📚 | VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners | 25.80 | 2022-12-09 | - |
| 3 | MAXI | MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge | 23.80 | 2023-03-15 | 📦 wlin-at/maxi |
| 4 | CLIP-Hitchhiker (ViT-B/16, 32 frames) | A CLIP-Hitchhiker's Guide to Long Video Retrieval | 21.10 | 2022-05-17 | 📦 m-bain/clip-hitchhiker |