List your company

Video Recognition on UCF-101 (test)

88.7AccuracyMoTE
57.08465.29273.581.708Oct 14, 2024

Evaluation results

MethodLinks
MoTEEncoder=ViT-L/14, Frames=8, Protocol=Zero-shot2024.1088.7
OTIEncoder=ViT-L/14, Frames=8, Protocol=Zero-shot2024.1088.1
Open-VCLIPEncoder=ViT-L/14, Frames=8, Protocol=Zero-shot2024.1087.6
Open-VCLIPEncoder=ViT-B/16, Frames=8, Protocol=Zero-shot2024.1083.4
MoTEEncoder=ViT-B/16, Frames=8, Protocol=Zero-shot2024.1083.4
OTIEncoder=ViT-B/16, Frames=8, Protocol=Zero-shot2024.1083.3
Text4VisEncoder=ViT-L/14, Frames=8, Protocol=Zero-shot2024.1082.6
MAXIEncoder=ViT-B/16, Frames=16/32, Protocol=Zero-shot2024.1078.2
ST-AdapterEncoder=ViT-B/16, Frames=8, Protocol=Zero-shot2024.1076.9
ViFi-CLIPEncoder=ViT-B/16, Frames=32, Protocol=Zero-shot2024.1076.8
Vita-CLIPEncoder=ViT-B/16, Frames=8/32, Protocol=Zero-shot2024.1075
DiSTEncoder=ViT-L/14, Frames=32, Protocol=Zero-shot2024.1074.9
X-FlorenceEncoder=Florence, Frames=32, Protocol=Zero-shot2024.1073.2
X-CLIPEncoder=ViT-B/16, Frames=32, Protocol=Zero-shot2024.1072
A5Encoder=ViT-B/16, Frames=32, Protocol=Zero-shot2024.1069.3
ActionCLIPEncoder=ViT-B/16, Frames=32, Protocol=Zero-shot2024.1058.3