More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation

Benchmark Model Rank Results
action-classification-on-kinetics-400bLVNet Fan et al. (2019)#144Acc@1: 73.5Acc@5: 91.2
action-recognition-in-videos-on-somethingbLVNet#78Top-1 Accuracy: 65.2