Multi-Fiber Networks for Video Recognition
Open paper
Benchmark
Model
Rank
Results
action-classification-on-kinetics-400
MFNet
–
Acc@1: 72.8
Acc@5: 90.4
action-recognition-in-videos-on-ucf101
MF-Net, RGB only (ImageNet+Kinetics pretrained)
–
3-fold Accuracy: 96.0
Rank counts only results with a code link.