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

Benchmark Model Rank Results
action-recognition-in-videos-on-something-something-v2bLVNet#81Top-1 Accuracy: 65.2
action-classification-on-kinetics-400bLVNet Fan et al. (2019)#159Acc@1: 73.5Acc@5: 91.2