Activity Recognition On Stanford40
Metriken
Top-3 Accuracy (%)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Top-3 Accuracy (%) | Paper Title | Repository |
|---|---|---|---|
| CLIP | 6.49 | Human Pose Descriptions and Subject-Focused Attention for Improved Zero-Shot Transfer in Human-Centric Classification Tasks | - |
| FocusCLIP | 10.47 | Human Pose Descriptions and Subject-Focused Attention for Improved Zero-Shot Transfer in Human-Centric Classification Tasks | - |
0 of 2 row(s) selected.