List your company
ResearchFormerly WizWand

Few-shot video recognition on HMDB-51

0.612Top-1 Acc (K=2)Zero-ViCLIP + MSTA + Lcc
0.36240.42720.4920.5568Nov 18, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Zero-ViCLIP + MSTA + LccGFLOPs=179.84, Transfer learning protocol=Efficient transfer pre-trained models, Multi-view inference=true2024.110.6120.6230.6710.704
MOTEGFLOPs=141, Transfer learning protocol=Tuning pre-trained models, Multi-view inference=true2024.110.610.6370.6690.685
Zero-ViCLIP + MSTAGFLOPs=179.84, Transfer learning protocol=Efficient transfer pre-trained models, Multi-view inference=true2024.110.6010.6220.6680.699
OSTTransfer learning protocol=Tuning pre-trained models, Multi-view inference=true2024.110.60.6250.6560.673
Zero-ViCLIP + AdaptFormerGFLOPs=179.80, Transfer learning protocol=Efficient transfer pre-trained models, Multi-view inference=true2024.110.60.6180.6660.701
Zero-ViCLIP + LORAGFLOPs=179.80, Transfer learning protocol=Efficient transfer pre-trained models, Multi-view inference=true2024.110.5940.6140.6650.694
Vanilla CLIPGFLOPs=282, Transfer learning protocol=Tuning pre-trained models, Multi-view inference=true2024.110.5780.6120.6560.667
ViFi-CLIPGFLOPs=281, Transfer learning protocol=Tuning pre-trained models, Multi-view inference=true2024.110.5750.6290.6470.666
ViCLIPGFLOPs=161, Transfer learning protocol=Tuning pre-trained models, Multi-view inference=true2024.110.5370.6040.6450.703
XCLIPGFLOPs=145, Transfer learning protocol=Adapting pre-trained models, Multi-view inference=true2024.110.5350.5780.6290.645
Zero-ViCLIPGFLOPs=161, Transfer learning protocol=Efficient transfer pre-trained models, Multi-view inference=true2024.110.4780.4780.4780.478
A5GFLOPs=284, Transfer learning protocol=Adapting pre-trained models, Multi-view inference=true2024.110.4120.5130.5650.627
Vanilla CLIPGFLOPs=281, Transfer learning protocol=Zero-shot pre-trained models, Multi-view inference=true2024.110.3720.3720.3720.372