Action Classification on UCF101
96.6Top-1 AccuracyTempPr†
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| TempPr†Backbone=MoViNet, Observation ratio=0.82026.04 | 96.6 | — | — | — | — | — | — | |
| EASTBackbone=MoViNet, Observation ratio=0.82026.04 | 96.5 | — | — | — | — | — | — | |
| EASTBackbone=MoViNet, Observation ratio=0.92026.04 | 96.5 | — | — | — | — | — | — | |
| EASTBackbone=MoViNet, Observation ratio=0.72026.04 | 96.4 | — | — | — | — | — | — | |
| TempPr†Backbone=MoViNet, Observation ratio=0.92026.04 | 96.2 | — | — | — | — | — | — | |
| EASTBackbone=MoViNet, Observation ratio=0.62026.04 | 96.1 | — | — | — | — | — | — | |
| ERAObservation ratio=0.92026.04 | 95.7 | — | — | — | — | — | — | |
| ERAObservation ratio=0.72026.04 | 95.5 | — | — | — | — | — | — | |
| EASTBackbone=MoViNet, Observation ratio=0.52026.04 | 95.5 | — | — | — | — | — | — | |
| TempPr†Backbone=MoViNet, Observation ratio=0.52026.04 | 95.4 | — | — | — | — | — | — | |
| TempPr†Backbone=MoViNet, Observation ratio=0.72026.04 | 95.3 | — | — | — | — | — | — | |
| TempPr†Backbone=MoViNet, Observation ratio=0.62026.04 | 95.2 | — | — | — | — | — | — | |
| FFNAdaptation Protocol=TTT2026.06 | 95 | — | — | — | — | — | — | |
| TempPr†Backbone=MoViNet, Observation ratio=0.32026.04 | 94.9 | — | — | — | — | — | — | |
| TempPr†Backbone=MoViNet, Observation ratio=0.42026.04 | 94.9 | — | — | — | — | — | — | |
| EASTBackbone=MoViNet, Observation ratio=0.42026.04 | 94.7 | — | — | — | — | — | — | |
| IGGNObservation ratio=0.92026.04 | 94.4 | — | — | — | — | — | — | |
| ERAObservation ratio=0.52026.04 | 94.2 | — | — | — | — | — | — | |
| Online TTTAdaptation Protocol=TTT-baseline2026.06 | 94.2 | — | — | — | — | — | — | |
| IGGNObservation ratio=0.72026.04 | 94.1 | — | — | — | — | — | — | |
| Web-DINOAdaptation Protocol=TTA baseline2026.06 | 94.1 | — | — | — | — | — | — | |
| EASTBackbone=VideoMAE, Observation ratio=0.82026.04 | 93.8 | — | — | — | — | — | — | |
| EASTBackbone=VideoMAE, Observation ratio=0.92026.04 | 93.8 | — | — | — | — | — | — | |
| EASTBackbone=MoViNet, Observation ratio=0.32026.04 | 93.8 | — | — | — | — | — | — | |
| DINOv2Adaptation Protocol=TTA baseline2026.06 | 93.8 | — | — | — | — | — | — | |
| V-JEPA 2Adaptation Protocol=TTA baseline2026.06 | 93.8 | — | — | — | — | — | — | |
| EASTBackbone=VideoMAE, Observation ratio=0.72026.04 | 93.7 | — | — | — | — | — | — | |
| Early-ViTBackbone=MoViNet, Observation ratio=0.72026.04 | 93.6 | — | — | — | — | — | — | |
| EASTBackbone=VideoMAE, Observation ratio=0.62026.04 | 93.6 | — | — | — | — | — | — | |
| Early-ViTBackbone=MoViNet, Observation ratio=0.82026.04 | 93.5 | — | — | — | — | — | — | |
| Early-ViTBackbone=MoViNet, Observation ratio=0.92026.04 | 93.5 | — | — | — | — | — | — | |
| TempPr†Backbone=MoViNet, Observation ratio=0.22026.04 | 93.5 | — | — | — | — | — | — | |
| DINOv3Adaptation Protocol=TTA baseline2026.06 | 93.5 | — | — | — | — | — | — | |
| Early-ViTBackbone=MoViNet, Observation ratio=0.62026.04 | 93.4 | — | — | — | — | — | — | |
| EASTBackbone=VideoMAE, Observation ratio=0.52026.04 | 93.4 | — | — | — | — | — | — | |
| TempPr‡Backbone=MoViNet, Observation ratio=0.92026.04 | 93.2 | — | — | — | — | — | — | |
| EASTBackbone=MoViNet, Observation ratio=0.22026.04 | 93.2 | — | — | — | — | — | — | |
| EASTBackbone=VideoMAE, Observation ratio=0.42026.04 | 93.1 | — | — | — | — | — | — | |
| RGN-KFObservation ratio=0.82026.04 | 93 | — | — | — | — | — | — | |
| RGN-KFObservation ratio=0.92026.04 | 92.9 | — | — | — | — | — | — | |
| IGGNObservation ratio=0.52026.04 | 92.9 | — | — | — | — | — | — | |
| Early-ViTBackbone=MoViNet, Observation ratio=0.52026.04 | 92.9 | — | — | — | — | — | — | |
| TempPr‡Backbone=MoViNet, Observation ratio=0.72026.04 | 92.8 | — | — | — | — | — | — | |
| TempPr‡Backbone=MoViNet, Observation ratio=0.52026.04 | 92.5 | — | — | — | — | — | — | |
| ERAObservation ratio=0.32026.04 | 92.4 | — | — | — | — | — | — | |
| RGN-KFObservation ratio=0.62026.04 | 92.3 | — | — | — | — | — | — | |
| Early-ViTBackbone=MoViNet, Observation ratio=0.42026.04 | 92.2 | — | — | — | — | — | — | |
| EASTBackbone=VideoMAE, Observation ratio=0.32026.04 | 92.2 | — | — | — | — | — | — | |
| RGN-KFObservation ratio=0.72026.04 | 92 | — | — | — | — | — | — | |
| DBDNetObservation ratio=0.92026.04 | 92 | — | — | — | — | — | — | |
| DBDNetObservation ratio=0.82026.04 | 91.9 | — | — | — | — | — | — | |
| GGNNObservation ratio=0.92026.04 | 91.8 | — | — | — | — | — | — | |
| DBDNetObservation ratio=0.72026.04 | 91.7 | — | — | — | — | — | — | |
| JVSObservation ratio=0.22026.04 | 91.7 | — | — | — | — | — | — | |
| Early-ViTBackbone=MoViNet, Observation ratio=0.32026.04 | 91.7 | — | — | — | — | — | — | |
| RGN-KFObservation ratio=0.52026.04 | 91.5 | — | — | — | — | — | — | |
| GGNNObservation ratio=0.72026.04 | 91.4 | — | — | — | — | — | — | |
| EASTBackbone=VideoMAE, Observation ratio=0.22026.04 | 91.4 | — | — | — | — | — | — | |
| TSObservation ratio=0.72026.04 | 91.3 | — | — | — | — | — | — | |
| TSObservation ratio=0.92026.04 | 91.3 | — | — | — | — | — | — | |
| EASTBackbone=MoViNet, Observation ratio=0.12026.04 | 91.3 | — | — | — | — | — | — | |
| TSObservation ratio=0.82026.04 | 91.2 | — | — | — | — | — | — | |
| DBDNetObservation ratio=0.62026.04 | 91.1 | — | — | — | — | — | — | |
| TSObservation ratio=0.62026.04 | 91 | — | — | — | — | — | — | |
| AAPNETObservation ratio=0.92026.04 | 90.9 | — | — | — | — | — | — | |
| TSObservation ratio=0.52026.04 | 90.9 | — | — | — | — | — | — | |
| GGNNObservation ratio=0.52026.04 | 90.9 | — | — | — | — | — | — | |
| RGN-KFObservation ratio=0.42026.04 | 90.6 | — | — | — | — | — | — | |
| DBDNetObservation ratio=0.52026.04 | 90.6 | — | — | — | — | — | — | |
| MSRNNObservation ratio=0.92026.04 | 90.4 | — | — | — | — | — | — | |
| TempPr‡Backbone=MoViNet, Observation ratio=0.32026.04 | 90.4 | — | — | — | — | — | — | |
| MSRNNObservation ratio=0.82026.04 | 90.3 | — | — | — | — | — | — | |
| Early-ViTBackbone=MoViNet, Observation ratio=0.22026.04 | 90.1 | — | — | — | — | — | — | |
| MSRNNObservation ratio=0.72026.04 | 89.9 | — | — | — | — | — | — | |
| AAPNETObservation ratio=0.82026.04 | 89.9 | — | — | — | — | — | — | |
| TSObservation ratio=0.42026.04 | 89.9 | — | — | — | — | — | — | |
| GGNNObservation ratio=0.32026.04 | 89.8 | — | — | — | — | — | — | |
| IGGNObservation ratio=0.32026.04 | 89.8 | — | — | — | — | — | — | |
| MSRNNObservation ratio=0.62026.04 | 89.7 | — | — | — | — | — | — | |
| mem-LSTMObservation ratio=0.92026.04 | 89.7 | — | — | — | — | — | — | |
| DBDNetObservation ratio=0.42026.04 | 89.7 | — | — | — | — | — | — | |
| mem-LSTMObservation ratio=0.82026.04 | 89.4 | — | — | — | — | — | — | |
| RACKObservation ratio=0.32026.04 | 89.4 | — | — | — | — | — | — | |
| MSRNNObservation ratio=0.52026.04 | 89.2 | — | — | — | — | — | — | |
| mem-LSTMObservation ratio=0.72026.04 | 89.1 | — | — | — | — | — | — | |
| ERAObservation ratio=0.12026.04 | 89.1 | — | — | — | — | — | — | |
| TSObservation ratio=0.32026.04 | 88.9 | — | — | — | — | — | — | |
| MSRNNObservation ratio=0.42026.04 | 88.8 | — | — | — | — | — | — | |
| mem-LSTMObservation ratio=0.62026.04 | 88.6 | — | — | — | — | — | — | |
| TempPr†Backbone=MoViNet, Observation ratio=0.12026.04 | 88.6 | — | — | — | — | — | — | |
| EASTBackbone=VideoMAE, Observation ratio=0.12026.04 | 88.6 | — | — | — | — | — | — | |
| GGNNObservation ratio=0.22026.04 | 88.5 | — | — | — | — | — | — | |
| mem-LSTMObservation ratio=0.52026.04 | 88.4 | — | — | — | — | — | — | |
| DBDNetObservation ratio=0.32026.04 | 88.4 | — | — | — | — | — | — | |
| AAPNETObservation ratio=0.62026.04 | 88.3 | — | — | — | — | — | — | |
| AAPNETObservation ratio=0.72026.04 | 88.3 | — | — | — | — | — | — | |
| MSRNNObservation ratio=0.32026.04 | 88.2 | — | — | — | — | — | — | |
| RGN-KFObservation ratio=0.32026.04 | 87.8 | — | — | — | — | — | — | |
| RACKObservation ratio=0.12026.04 | 87.6 | — | — | — | — | — | — | |
| RACKObservation ratio=0.22026.04 | 87.6 | — | — | — | — | — | — |