Action Recognition In Videos On Thumos14
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Paper Title | Repository | ||
|---|---|---|---|---|
| Dai et. al. | 33.3 | 25.6 | Temporal Context Network for Activity Localization in Videos | - |
| SSN | 41.0 | 29.8 | Temporal Action Detection with Structured Segment Networks | |
| BSN | 45.0 | 36.9 | BSN: Boundary Sensitive Network for Temporal Action Proposal Generation | |
| MGG UNet | 46.8 | 37.4 | Multi-granularity Generator for Temporal Action Proposal | - |
| Yeung et. al. | 26.4 | 17.1 | End-to-end Learning of Action Detection from Frame Glimpses in Videos | |
| BMN | 47.4 | 38.8 | BMN: Boundary-Matching Network for Temporal Action Proposal Generation | |
| Single-stream R-C3D + OHEM | 43.1 | 35.8 | Two-Stream Region Convolutional 3D Network for Temporal Activity Detection | - |
| Two-stream R-C3D (Sum) + OHEM | 43.0 | 36.1 | Two-Stream Region Convolutional 3D Network for Temporal Activity Detection | - |
| Shou et. al. | 28.7 | 19.0 | Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs | |
| TURN | 35.3 | 24.5 | TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals |
0 of 10 row(s) selected.