List your company
ResearchFormerly WizWand

Video Recognition on HMDB51 (test)

61.4AccuracyMoTE
23.33633.21843.152.982Jul 4, 2022Nov 19, 2022Apr 7, 2023Aug 24, 2023Jan 10, 2024May 28, 2024Oct 14, 2024
Updated 8mo ago

Evaluation results

MethodLinks
MoTEEncoder=ViT-L/14, Frames=8, Protocol=Zero-shot2024.1061.4——
OTIEncoder=ViT-L/14, Frames=8, Protocol=Zero-shot2024.1059.3——
Open-VCLIPEncoder=ViT-L/14, Frames=8, Protocol=Zero-shot2024.1059——
DiSTEncoder=ViT-L/14, Frames=32, Protocol=Zero-shot2024.1057.5——
MoTEEncoder=ViT-B/16, Frames=8, Protocol=Zero-shot2024.1055.8——
OTIEncoder=ViT-B/16, Frames=8, Protocol=Zero-shot2024.1054.2——
Open-VCLIPEncoder=ViT-B/16, Frames=8, Protocol=Zero-shot2024.1053.9——
Text4VisEncoder=ViT-L/14, Frames=8, Protocol=Zero-shot2024.1052.4——
MAXIEncoder=ViT-B/16, Frames=16/32, Protocol=Zero-shot2024.1052.3——
ST-AdapterEncoder=ViT-B/16, Frames=8, Protocol=Zero-shot2024.1051.5——
ViFi-CLIPEncoder=ViT-B/16, Frames=32, Protocol=Zero-shot2024.1051.3——
Text4VisZero-shot=true2022.0749.8——
Vita-CLIPEncoder=ViT-B/16, Frames=8/32, Protocol=Zero-shot2024.1048.6——
X-FlorenceEncoder=Florence, Frames=32, Protocol=Zero-shot2024.1048.4——
X-CLIPEncoder=ViT-B/16, Frames=32, Protocol=Zero-shot2024.1044.6——
A5Encoder=ViT-B/16, Frames=32, Protocol=Zero-shot2024.1044.3——
ActionCLIPEncoder=ViT-B/16, Frames=32, Protocol=Zero-shot2024.1040.8——
ResTZero-shot=true2022.0734.4——
E2EZero-shot=true2022.0724.8——
AdaptFormer-64Avg. Params (M)=1.26, Pre-training=Supervised2022.05—73.21—
ADMM-based TT-format LSTMComp. Method=TT, # Para.=0.20M2021.07—64.0984
Full-tuningAvg. Params (M)=86.04, Pre-training=Supervised2022.05—59.38—
LinearAvg. Params (M)=0.07, Pre-training=Supervised2022.05—70.31—
PSTRN-MComp. Method=TR, # Para.=0.36M2021.07—59.6746.7
PSTRN-SComp. Method=TR, # Para.=0.48M2021.07—60.0434.7
TR-LSTMComp. Method=TR, # Para.=0.67M2021.07—63.825
TT-LSTMComp. Method=TT, # Para.=0.67M2021.07—62.2425
UncompressedComp. Method=-, # Para.=16.8M2021.07—62.91
VPTAvg. Params (M)=0.08, Pre-training=Supervised2022.05—71.56—