Zero Shot Action Recognition On Charades 1
Metrics
mAP
Results
Performance results of various models on this benchmark
Model Name | mAP | Paper Title | Repository |
|---|---|---|---|
| MAXI | 23.8 | MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge | - |
| CLIP-Hitchhiker (ViT-B/16, 32 frames) | 21.1 | A CLIP-Hitchhiker's Guide to Long Video Retrieval | - |
| MSQNet | 35.59 | Actor-agnostic Multi-label Action Recognition with Multi-modal Query | - |
| VideoCoCa | 25.8 | VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners | - |
0 of 4 row(s) selected.