Action Recognition In Videos On Something 3
评估指标
Top-1 Accuracy
Top-5 Accuracy
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | |||
|---|---|---|---|---|
| STM (16 frames, ImageNet pretraining) | 64.2 | 89.8 | STM: SpatioTemporal and Motion Encoding for Action Recognition | - |
| CPNet Res34, 5 CP | 57.65 | 83.95 | Learning Video Representations from Correspondence Proposals | |
| 2-Stream TRN | 55.52 | 83.06 | Temporal Relational Reasoning in Videos | |
| DIN | 34.11 | - | DenseImage Network: Video Spatial-Temporal Evolution Encoding and Understanding | - |
0 of 4 row(s) selected.