Spatio Temporal Action Localization On Ava
Metrics
val mAP
Results
Performance results of various models on this benchmark
Model Name | val mAP | Paper Title | Repository |
|---|---|---|---|
| InternVideo | 41.01 | InternVideo: General Video Foundation Models via Generative and Discriminative Learning | |
| RM (multi-scale, ir-CSN-152) | 37.95 | Relation Modeling in Spatio-Temporal Action Localization | - |
| VideoMAE V2-g | 42.6 | VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking | |
| STAR/L | 41.7 | End-to-End Spatio-Temporal Action Localisation with Video Transformers | - |
| RM (multi-scale, ensemble) | 40.52 | Relation Modeling in Spatio-Temporal Action Localization | - |
| ACAR (multi-scale, R-101, 8 × 8) | 36.36 | Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization | |
| ACAR (multi-scale, ensemble) | 40.49 | Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization |
0 of 7 row(s) selected.