ConvNet Architecture Search for Spatiotemporal Feature Learning
Open paper
Benchmark
Model
Rank
Results
action-recognition-in-videos-on-hmdb-51
Res3D
#46
Average accuracy of 3 splits: 54.9
action-recognition-in-videos-on-ucf101
Res3D
#51
3-fold Accuracy: 85.8
action-classification-on-kinetics-400
TSN
#156
Acc@1: 73.9
Rank counts only results with a code link.