Video Recognition on UCF-101
78.7Top-1 AccViCLIP + MSTA + LCC
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ViCLIP + MSTA + LCCFrames=8, Zero-shot transfer=true, Inference=single-view2024.11 | 78.7 | — | |
| OSTFrames=8, Zero-shot transfer=true, Inference=single-view2024.11 | 77.9 | — | |
| ViCLIP + MSTAFrames=8, Zero-shot transfer=true, Inference=single-view2024.11 | 77.8 | — | |
| ViCLIP + LORAFrames=8, Zero-shot transfer=true, Inference=single-view2024.11 | 77.3 | — | |
| ViCLIP + AdaptFormerFrames=8, Zero-shot transfer=true, Inference=single-view2024.11 | 77.2 | — | |
| ViCLIPFrames=8, Zero-shot transfer=true, Inference=single-view2024.11 | 77.1 | — | |
| ViFi-CLIPFrames=32, Zero-shot transfer=true, Inference=single-view2024.11 | 76.8 | — | |
| Vita-CLIPFrames=32, Zero-shot transfer=true, Inference=single-view2024.11 | 75 | — | |
| XCLIPFrames=32, Zero-shot transfer=true, Inference=single-view2024.11 | 72 | — | |
| A5Frames=8/32, Zero-shot transfer=true, Inference=single-view2024.11 | 69.3 | — | |
| Vanilla CLIPFrames=32, Zero-shot transfer=true, Inference=single-view2024.11 | 63.2 | — | |
| Zero-ViCLIPFrames=8, Zero-shot transfer=true, Inference=single-view2024.11 | 62.6 | — | |
| JigsawNetFrames=16, Zero-shot transfer=true, Inference=single-view2024.11 | 56 | — | |
| ER-ZSARFrames=16, Zero-shot transfer=true, Inference=single-view2024.11 | 51.8 | — |