Few-Shot Action Recognition on HMDB (5-way K-shot Evaluation)
82.6AccuracyDIST
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DISTPre-training=CLIP-ViT-B2026.02 | 82.6 | — | — | |
| CLIP-FSARPre-training=CLIP-ViT-B2026.02 | 75.8 | — | — | |
| TEAMPre-training=INet-ViT-B2026.02 | 70.9 | — | — | |
| CLIP-FSARPre-training=CLIP-RN502026.02 | 69.2 | — | — | |
| MVP-shotPre-training=CLIP-ViT-B2026.02 | 69.2 | — | — | |
| Lite-MKDPre-training=INet-RN502026.02 | 66.9 | — | — | |
| CapFSARPre-training=BLIP-ViT-B2026.02 | 65.2 | — | — | |
| GgHMPre-training=INet-RN502026.02 | 61.2 | — | — | |
| MoLoPre-training=INet-RN502026.02 | 60.8 | — | — | |
| HyRSMPre-training=INet-RN502026.02 | 60.3 | — | — | |
| AmeFu-NetPre-training=INet-RN502026.02 | 60.2 | — | — | |
| CPMPre-training=INet-RN502026.02 | 60.1 | — | — | |
| TA2NPre-training=INet-RN502026.02 | 59.7 | — | — | |
| HCLPre-training=INet-RN502026.02 | 59.1 | — | — | |
| MTFANPre-training=INet-RN502026.02 | 59 | — | — | |
| CLIP-FreezePre-training=CLIP-ViT-B2026.02 | 58.2 | — | — | |
| OTAMPre-training=INet-RN502026.02 | 54.5 | — | — | |
| ProtoNetPre-training=INet-RN502026.02 | 54.2 | — | — | |
| TRXPre-training=INet-RN502026.02 | 53.1 | — | — | |
| STRMPre-training=INet-RN502026.02 | 52.3 | — | — | |
| ARNPre-training=C3D2026.02 | 45.5 | — | — | |
| CapFSARModality=Multi-modal, Pre-training=BLIP-ViT-B, Tuning=FFT2024.11 | — | 70.3 | 81.3 | |
| CLIPModality=Multi-modal, Pre-training=CLIP-ViT-B, Tuning=Frozen2024.11 | — | 58.2 | 77 | |
| CLIP-CPM2CModality=Multi-modal, Pre-training=CLIP-ViT-B, Tuning=FFT2024.11 | — | 75.9 | 88 | |
| CLIP-FSARModality=Multi-modal, Pre-training=CLIP-ViT-B, Tuning=FFT2024.11 | — | 75.8 | 87.7 | |
| HyRSMModality=Unimodal, Pre-training=BLIP-ViT-B(V), Tuning=FFT2024.11 | — | 69.8 | 80.6 | |
| MASTAFModality=Unimodal, Pre-training=JFT-ViT-B, Tuning=FFT2024.11 | — | 69.5 | — | |
| OTAMModality=Unimodal, Pre-training=CLIP-ViT-B(V), Tuning=FFT2024.11 | — | 72.5 | 83.9 | |
| TAMTModality=Unimodal, Pre-training=ViT-B, Tuning=PEFT2024.11 | — | 77.7 | 88.2 | |
| TRXModality=Unimodal, Pre-training=BLIP-ViT-B(V), Tuning=FFT2024.11 | — | 58.9 | 79.9 |