Action Recognition On Hacs
Metriken
Top 1 Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Top 1 Accuracy | Paper Title | Repository |
|---|---|---|---|
| InternVideo2-6B | 97.0 | InternVideo2: Scaling Foundation Models for Multimodal Video Understanding | |
| SRTG r(2+1)d-101 | 84.33 | Learn to cycle: Time-consistent feature discovery for action recognition | |
| SRTG r3d-34 | 78.60 | Learn to cycle: Time-consistent feature discovery for action recognition | |
| SRTG r3d-101 | 81.66 | Learn to cycle: Time-consistent feature discovery for action recognition | |
| UniFormerV2-L | 95.5 | UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer | |
| SRTG r(2+1)d-50 | 83.77 | Learn to cycle: Time-consistent feature discovery for action recognition | |
| SRTG r(2+1)d-34 | 80.39 | Learn to cycle: Time-consistent feature discovery for action recognition | |
| SRTG r3d-50 | 80.36 | Learn to cycle: Time-consistent feature discovery for action recognition |
0 of 8 row(s) selected.