Space-time Mixing Attention for Video Transformer
Open paper
Benchmark
Model
Rank
Results
action-classification-on-kinetics-600
XViT (x16)
#26
Top-1 Accuracy: 84.5
Top-5 Accuracy: 96.3
action-recognition-in-videos-on-something
X-Vit (x16)
#59
Top-1 Accuracy: 67.2
Top-5 Accuracy: 90.8
Parameters: N/A
…
Rank counts only results with a code link.