CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition
Open paper
Benchmark
Model
Rank
Results
image-classification-on-imagenet
CoDAT-L
#684
Top 1 Accuracy: 81.4%
image-classification-on-imagenet
CoDAT-M
#784
Top 1 Accuracy: 79.7%
image-classification-on-imagenet
CoDAT-S
#910
Top 1 Accuracy: 77.6%
Rank counts only results with a code link.