Action Recognition In Videos
Action Recognition in Videos is a task in computer vision and pattern recognition where the goal is to identify and categorize human actions performed in a video sequence. The task involves analyzing the spatiotemporal dynamics of the actions and mapping them to a predefined set of action classes, such as running, jumping, or swimming.
Papers
Showing 1–10 of 124 papers
All datasetsJester (Gesture Recognition)PKU-MMDUCF101Something-Something V2Kinetics 400AVA v2.2FS-Something-Something V2-FullFS-Something-Something V2-SmallSports-1MTHUMOS14ActivityNetAVA v2.1
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | CPNet Res34, 5 CP | Val | 96.7 | — | Unverified |
| 2 | STM (Resnet-50, 16 frames) | Val | 96.7 | — | Unverified |
| 3 | MFNet | Val | 96.68 | — | Unverified |
| 4 | MultiScale TRN | Val | 95.31 | — | Unverified |
| 5 | DIN | Val | 95.31 | — | Unverified |
| 6 | convSTAR | Val | 92.7 | — | Unverified |
| 7 | 3D-SqueezeNet | Val | 90.77 | — | Unverified |
| 8 | 3D-ShuffleNetV2 0.25x | Val | 86.91 | — | Unverified |
| 9 | 3D-MobileNetV2 0.2x | Val | 86.43 | — | Unverified |