Is Space-Time Attention All You Need for Video Understanding?

Benchmark Model Rank Results
anomaly-detection-on-ubnormalTimeSformer#6AUC: 68.5%RBDC: 0.04TBDC: 0.05
action-recognition-on-diving-48TimeSformer-L#12Accuracy: 81
action-recognition-on-diving-48TimeSformer-HR#13Accuracy: 78
action-recognition-on-diving-48TimeSformer#15Accuracy: 75
action-classification-on-kinetics-600TimeSformer-L (extra data)#37Top-1 Accuracy: 82.2
action-classification-on-kinetics-400TimeSformer-L#87Acc@1: 80.7Acc@5: 94.7FLOPs (G) x views: 7140x3…
action-classification-on-kinetics-400TimeSformer-HR#102Acc@1: 79.7Acc@5: 94.4
action-classification-on-kinetics-400TimeSformer#125Acc@1: 78Acc@5: 93.7
action-recognition-in-videos-on-something-something-v2TimeSformer-HR#93Top-1 Accuracy: 62.5
action-recognition-in-videos-on-something-something-v2TimeSformer-L#94Top-1 Accuracy: 62.3
action-recognition-in-videos-on-something-something-v2TimeSformer#99Top-1 Accuracy: 59.5