Temporally-Adaptive Models for Efficient Video Understanding

Benchmark Model Rank Results
action-recognition-on-epic-kitchens-100TAdaFormer-L/14#4Action@1: 51.8Verb@1: 71.7Noun@1: 64.1
action-recognition-on-epic-kitchens-100TAdaConvNeXtV2-S#9Action@1: 48.9Verb@1: 71.0Noun@1: 60.2
action-recognition-in-videos-on-something-something-v1TAdaFormer-L/14#5Top 1 Accuracy: 63.7
action-recognition-in-videos-on-something-something-v1TAdaConvNeXtV2-B#9Top 1 Accuracy: 60.7
action-classification-on-kinetics-400TAdaFormer-L/14#12Acc@1: 89.9
action-classification-on-kinetics-400TAdaConvNeXtV2-B#43Acc@1: 86.4
action-recognition-in-videos-on-something-something-v2TAdaFormer-L/14#20Top-1 Accuracy: 73.6
action-recognition-in-videos-on-something-something-v2TAdaConvNeXtV2-B#31Top-1 Accuracy: 71.1