Space-time Mixing Attention for Video Transformer

Benchmark Model Rank Results
action-classification-on-kinetics-600XViT (x16)#26Top-1 Accuracy: 84.5Top-5 Accuracy: 96.3
action-recognition-in-videos-on-something-something-v2X-Vit (x16)#62Top-1 Accuracy: 67.2Top-5 Accuracy: 90.8Parameters: N/A…