List your company
ResearchFormerly WizWand

Few-shot video recognition on UCF-101

88.1Top-1 Acc (K=2)MOTE
47.74858.22468.779.176Nov 18, 2024
Updated 8mo ago

Evaluation results

MethodLinks
MOTEGFLOPs=141, Transfer learning protocol=Tuning pre-trained models, Multi-view inference=true2024.1188.190.792.293.7
Zero-ViCLIP + MSTA + LccGFLOPs=179.84, Transfer learning protocol=Efficient transfer pre-trained models, Multi-view inference=true2024.1186.190.292.794.8
Zero-ViCLIP + MSTAGFLOPs=179.84, Transfer learning protocol=Efficient transfer pre-trained models, Multi-view inference=true2024.1185.18992.393.5
Zero-ViCLIP + AdaptFormerGFLOPs=179.80, Transfer learning protocol=Efficient transfer pre-trained models, Multi-view inference=true2024.1184.888.791.793.3
Zero-ViCLIP + LORAGFLOPs=179.80, Transfer learning protocol=Efficient transfer pre-trained models, Multi-view inference=true2024.1183.588.390.992.7
OSTTransfer learning protocol=Tuning pre-trained models, Multi-view inference=true2024.118388.491.393.9
ViCLIPGFLOPs=161, Transfer learning protocol=Tuning pre-trained models, Multi-view inference=true2024.11838892.193.2
Vanilla CLIPGFLOPs=282, Transfer learning protocol=Tuning pre-trained models, Multi-view inference=true2024.1181.886.390.192.5
ViFi-CLIPGFLOPs=281, Transfer learning protocol=Tuning pre-trained models, Multi-view inference=true2024.1180.585.390.293.2
A5GFLOPs=284, Transfer learning protocol=Adapting pre-trained models, Multi-view inference=true2024.1171.780.385.990.3
Zero-ViCLIPGFLOPs=161, Transfer learning protocol=Efficient transfer pre-trained models, Multi-view inference=true2024.1171717171
Vanilla CLIPGFLOPs=281, Transfer learning protocol=Zero-shot pre-trained models, Multi-view inference=true2024.1162.862.862.862.8
XCLIPGFLOPs=145, Transfer learning protocol=Adapting pre-trained models, Multi-view inference=true2024.1149.376.284.191.6