More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation
Open paper
Benchmark
Model
Rank
Results
action-classification-on-kinetics-400
bLVNet Fan et al. (2019)
#144
Acc@1: 73.5
Acc@5: 91.2
action-recognition-in-videos-on-something
bLVNet
#78
Top-1 Accuracy: 65.2
Rank counts only results with a code link.