Extending Video Masked Autoencoders to 128 frames

Open paper
Benchmark Model Rank Results
action-recognition-on-diving-48LVMAE–Accuracy: 94.9
action-recognition-on-epic-kitchens-100LVMAE–Action@1: 52.1Verb@1: 75.0Noun@1: 61.8

Rank counts only results with a code link.