List your company
ResearchFormerly WizWand

Video Classification on UCF-101 (val)

91.4AccuracyTACO
56.97665.91374.8583.787Apr 17, 2026Apr 28, 2026May 9, 2026May 21, 2026Jun 1, 2026Jun 12, 2026Jun 24, 2026
Updated 4mo ago

Evaluation results

MethodLinks
TACOEncoder=ViT-L/14, Frames=8, Zero-shot=true2026.0691.4
MoTEEncoder=ViT-L/14, Frames=8, Zero-shot=true2026.0688.7
OTIEncoder=ViT-L/14, Frames=8, Zero-shot=true2026.0688.1
Open-VCLIPEncoder=ViT-L/14, Frames=8, Zero-shot=true2026.0687.6
TACOEncoder=ViT-B/16, Frames=8, Zero-shot=true2026.0685.6
FROSTEREncoder=ViT-B/16, Frames=8, Zero-shot=true2026.0684.8
Open-MeDeEncoder=ViT-B/16, Frames=8, Zero-shot=true2026.0683.7
Open-VCLIPEncoder=ViT-B/16, Frames=8, Zero-shot=true2026.0683.4
MoTEEncoder=ViT-B/16, Frames=8, Zero-shot=true2026.0683.4
Text4VisEncoder=ViT-L/14, Frames=8, Zero-shot=true2026.0682.6
CATISModel=VideoMAE ViT-B, r=160, start layer=3, GFLOPs=214.1, Tokens=128, Reduction=91.8%2026.0481.73
VanillaModel=VideoMAE ViT-B, r=160, start layer=3, GFLOPs=315.4, Tokens=15682026.0481.26
ToMeModel=VideoMAE ViT-B, r=160, start layer=3, GFLOPs=214.1, Tokens=128, Reduction=91.8%2026.0481.23
ToFuModel=VideoMAE ViT-B, r=160, start layer=3, GFLOPs=214.1, Tokens=128, Reduction=91.8%2026.0480.94
PiToMeModel=VideoMAE ViT-B, r=160, start layer=3, GFLOPs=214.1, Tokens=128, Reduction=91.8%2026.0480.47
MCTFModel=VideoMAE ViT-B, r=160, start layer=3, GFLOPs=214.1, Tokens=128, Reduction=91.8%2026.0479.83
MAXIEncoder=ViT-B/16, Frames=16/32, Zero-shot=true2026.0678.2
OSTEncoder=ViT-B/16, Frames=8, Zero-shot=true2026.0677.9
ST-AdapterEncoder=ViT-B/16, Frames=8, Zero-shot=true2026.0676.9
ViFi-CLIPEncoder=ViT-B/16, Frames=32, Zero-shot=true2026.0676.8
Vita-CLIPEncoder=ViT-B/16, Frames=8/32, Zero-shot=true2026.0675
DiSTEncoder=ViT-L/14, Frames=32, Zero-shot=true2026.0674.9
X-FlorenceEncoder=Florence, Frames=32, Zero-shot=true2026.0673.2
X-CLIPEncoder=ViT-B/16, Frames=32, Zero-shot=true2026.0672
ActionCLIPEncoder=ViT-B/16, Frames=32, Zero-shot=true2026.0658.3