Video Classification on UCF-101
91.2Avg AccDINOv2
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DINOv2Arch=ViT-g/14, Protocol=Frozen linear probe, Input frames=82023.04 | 91.2 | — | |
| OpenCLIPArch=ViT-G/14, Protocol=Frozen linear probe, Input frames=82023.04 | 90.7 | — | |
| DINOv2Arch=ViT-L/14, Protocol=Frozen linear probe, Input frames=82023.04 | 90.5 | — | |
| DINOv2Arch=ViT-B/14, Protocol=Frozen linear probe, Input frames=82023.04 | 89.1 | — | |
| iBOTArch=ViT-L/16, Protocol=Frozen linear probe, Input frames=82023.04 | 88.6 | — | |
| DINOv2Arch=ViT-S/14, Protocol=Frozen linear probe, Input frames=82023.04 | 87 | — | |
| DINOArch=ViT-B/8, Protocol=Frozen linear probe, Input frames=82023.04 | 85 | — | |
| EVA-CLIP-18BZero-shot=true, #Frames=162024.02 | 79.8 | 88.4 | |
| EVA-CLIP-18BZero-shot=true, #Frames=82024.02 | 79.7 | 88.2 | |
| EVA-CLIP-18BZero-shot=true, #Frames=12024.02 | 75 | 86 | |
| InternVL-CZero-shot=true, #Frames=12024.02 | 73.7 | 85.2 | |
| EVA-CLIP-8BZero-shot=true, #Frames=12024.02 | 73.6 | 85.7 | |
| EVA-02-CLIP-E/14+Zero-shot=true, #Frames=12024.02 | 72.1 | 83.1 | |
| MAEArch=ViT-H/14, Protocol=Frozen linear probe, Input frames=82023.04 | 70.6 | — | |
| EVA-01-CLIP-g/14+Zero-shot=true, #Frames=12024.02 | 68.8 | 78.9 | |
| OpenCLIP-G/14Zero-shot=true, #Frames=12024.02 | 68.7 | 80.5 | |
| DFN5B-CLIP-H/14+Zero-shot=true, #Frames=12024.02 | 68.4 | 79.2 | |
| DFN5B-CLIP-H/14Zero-shot=true, #Frames=12024.02 | 67 | 78.2 | |
| EVA-01-CLIP-g/14Zero-shot=true, #Frames=12024.02 | 66.2 | 76 | |
| MemDPCProtocol=linear probe2025.05 | — | 54.1 | |
| Video-GPTProtocol=linear probe2025.05 | — | 58.9 | |
| VideoMAEv2Protocol=linear probe2025.05 | — | 56.4 |