Video Recognition on HMDB-51
55.8Top-1 AccViCLIP + MSTA + LCC
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ViCLIP + MSTA + LCCFrames=8, Zero-shot transfer=true, Inference=single-view2024.11 | 55.8 | — | |
| ViCLIP + MSTAFrames=8, Zero-shot transfer=true, Inference=single-view2024.11 | 55.3 | — | |
| OSTFrames=8, Zero-shot transfer=true, Inference=single-view2024.11 | 54.9 | — | |
| ViCLIP + LORAFrames=8, Zero-shot transfer=true, Inference=single-view2024.11 | 54.2 | — | |
| ViCLIP + AdaptFormerFrames=8, Zero-shot transfer=true, Inference=single-view2024.11 | 54.1 | — | |
| ViCLIPFrames=8, Zero-shot transfer=true, Inference=single-view2024.11 | 51.9 | — | |
| ViFi-CLIPFrames=32, Zero-shot transfer=true, Inference=single-view2024.11 | 51.3 | — | |
| Vita-CLIPFrames=32, Zero-shot transfer=true, Inference=single-view2024.11 | 48.6 | — | |
| XCLIPFrames=32, Zero-shot transfer=true, Inference=single-view2024.11 | 44.6 | — | |
| A5Frames=8/32, Zero-shot transfer=true, Inference=single-view2024.11 | 44.3 | — | |
| Vanilla CLIPFrames=32, Zero-shot transfer=true, Inference=single-view2024.11 | 40.8 | — | |
| Zero-ViCLIPFrames=8, Zero-shot transfer=true, Inference=single-view2024.11 | 39.8 | — | |
| JigsawNetFrames=16, Zero-shot transfer=true, Inference=single-view2024.11 | 38.7 | — | |
| ER-ZSARFrames=16, Zero-shot transfer=true, Inference=single-view2024.11 | 35.3 | — |