List your company
ResearchFormerly WizWand

Video Action Classification on UCF101

89.7Top-1 AccVATT + Both
77.563280.714183.86587.0159Nov 3, 2022
Updated 8mo ago

Evaluation results

MethodLinks
VATT + BothPre-training Dataset=HT100M + AudioSet + YT8M, Cross-Modality Gradient Realignment (GR)=true, Gradient-based Curriculum Learning (CL)=true2022.1189.798.35
VATT + CLPre-training Dataset=HT100M + AudioSet + YT8M, Gradient-based Curriculum Learning (CL)=true2022.1189.0298.33
VATTPre-training Dataset=HT100M + AudioSet + YT8M2022.1188.2898.73
VATT + RW (VT)Pre-training Dataset=HT100M + AudioSet + YT8M, Gradient Re-weighting (RW)=Video-Text2022.1188.1997.96
VATT + GRPre-training Dataset=HT100M + AudioSet + YT8M, Cross-Modality Gradient Realignment (GR)=true2022.1187.4998.1
VATT + RW (VA)Pre-training Dataset=HT100M + AudioSet + YT8M, Gradient Re-weighting (RW)=Video-Audio2022.1186.9798.09
VATT + CLPre-training Dataset=HT100M + AudioSet, Gradient-based Curriculum Learning (CL)=true2022.1186.0497.75
VATT + BothPre-training Dataset=HT100M + AudioSet, Cross-Modality Gradient Realignment (GR)=true, Gradient-based Curriculum Learning (CL)=true2022.1185.4697.58
VATT + GRPre-training Dataset=HT100M + AudioSet, Cross-Modality Gradient Realignment (GR)=true2022.1184.7797.38
VATT + RW (VT)Pre-training Dataset=HT100M + AudioSet, Gradient Re-weighting (RW)=Video-Text2022.1184.4297.49
VATTPre-training Dataset=HT100M + AudioSet2022.1184.4—
VATT + RW (VA)Pre-training Dataset=HT100M + AudioSet, Gradient Re-weighting (RW)=Video-Audio2022.1183.4497.28
VATT + BothPre-training Dataset=HT100M, Cross-Modality Gradient Realignment (GR)=true, Gradient-based Curriculum Learning (CL)=true2022.1179.2496.58
VATT + CLPre-training Dataset=HT100M, Gradient-based Curriculum Learning (CL)=true2022.1179.196.16
VATTPre-training Dataset=HT100M2022.1178.5395.24
VATT + GRPre-training Dataset=HT100M, Cross-Modality Gradient Realignment (GR)=true2022.1178.4495.37
VATT + RW (VA)Pre-training Dataset=HT100M, Gradient Re-weighting (RW)=Video-Audio2022.1178.2495.01
VATT + RW (VT)Pre-training Dataset=HT100M, Gradient Re-weighting (RW)=Video-Text2022.1178.0395.35