Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition
Open paper
Benchmark
Model
Rank
Results
few-shot-action-recognition-on-hmdb51
Learn2Aug + TRX
–
1:1 Accuracy: 76.4
few-shot-action-recognition-on-ucf101
Learn2Aug + TRX
–
1:1 Accuracy: 96.5
Rank counts only results with a code link.