Action Recognition
Action Recognition is a computer vision task that involves recognizing human actions in videos or images. The goal is to classify and categorize the actions being performed in the video or image into a predefined set of action classes.
In the video domain, it is an open question whether training an action classification network on a sufficiently large dataset, will give a similar boost in performance when applied to a different temporal task or dataset. The challenges of building video datasets has meant that most popular benchmarks for action recognition are small, having on the order of 10k videos.
Please note some benchmarks may be located in the Action Classification or Video Classification tasks, e.g. Kinetics-400.
Papers
Showing 1–10 of 2759 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | LART (Hiera-H, K700 PT+FT) | mAP | 45.1 | — | Unverified |
| 2 | Hiera-H (K700 PT+FT) | mAP | 43.3 | — | Unverified |
| 3 | VideoMAE V2-g | mAP | 42.6 | — | Unverified |
| 4 | STAR/L | mAP | 41.7 | — | Unverified |
| 5 | MVD (Kinetics400 pretrain+finetune, ViT-H, 16x4) | mAP | 41.1 | — | Unverified |
| 6 | InternVideo | mAP | 41.01 | — | Unverified |
| 7 | MVD (Kinetics400 pretrain, ViT-H, 16x4) | mAP | 40.1 | — | Unverified |
| 8 | UMT-L (ViT-L/16) | mAP | 39.8 | — | Unverified |
| 9 | MaskFeat (Kinetics-600 pretrain, MViT-L) | mAP | 39.8 | — | Unverified |
| 10 | VideoMAE (K400 pretrain+finetune, ViT-H, 16x4) | mAP | 39.5 | — | Unverified |