MVFNet-ResNet50 (center crop, 8+16 ensemble, ImageNet pretrained, RGB only)

Reported on 2 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Robots1 result

Activity RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2020-12-13
66.3
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
MVFNet: Multi-View Fusion Network for Efficient Video Recognition arXiv:2012.06977

Time Series1 result

Action RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2020-12-13
66.3
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
MVFNet: Multi-View Fusion Network for Efficient Video Recognition arXiv:2012.06977