Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MSNet-R50 (16 frames, ImageNet pretrained)

MSNet-R50 (16 frames, ImageNet pretrained)

Reported on 11 benchmarks across 3 tasks · 1 paper

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

Robots5 results

Activity RecognitiononHMDB-51
Average accuracy of 3 splits· 2020-07-20
77.4
best: 88.7 (VideoMAE V2-g)
MotionSqueeze: Neural Motion Feature Learning for Video Understanding arXiv:2007.09933
Activity RecognitiononSomething-Something V1
Top 1 Accuracy· uses extra data· 2020-07-20
52.1
best: 70 (InternVideo)
MotionSqueeze: Neural Motion Feature Learning for Video Understanding arXiv:2007.09933
Activity RecognitiononSomething-Something V1
Top 5 Accuracy· uses extra data· 2020-07-20
82.3
best: 91.9 (VideoMAE V2-g)
MotionSqueeze: Neural Motion Feature Learning for Video Understanding arXiv:2007.09933
Activity RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2020-07-20
64.7
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
MotionSqueeze: Neural Motion Feature Learning for Video Understanding arXiv:2007.09933
Activity RecognitiononSomething-Something V2
Top-5 Accuracy· uses extra data· 2020-07-20
89.4
best: 96.3 (DejaVid)
MotionSqueeze: Neural Motion Feature Learning for Video Understanding arXiv:2007.09933

Time Series5 results

Action RecognitiononHMDB-51
Average accuracy of 3 splits· 2020-07-20
77.4
best: 88.7 (VideoMAE V2-g)
MotionSqueeze: Neural Motion Feature Learning for Video Understanding arXiv:2007.09933
Action RecognitiononSomething-Something V1
Top 1 Accuracy· uses extra data· 2020-07-20
52.1
best: 70 (InternVideo)
MotionSqueeze: Neural Motion Feature Learning for Video Understanding arXiv:2007.09933
Action RecognitiononSomething-Something V1
Top 5 Accuracy· uses extra data· 2020-07-20
82.3
best: 91.9 (VideoMAE V2-g)
MotionSqueeze: Neural Motion Feature Learning for Video Understanding arXiv:2007.09933
Action RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2020-07-20
64.7
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
MotionSqueeze: Neural Motion Feature Learning for Video Understanding arXiv:2007.09933
Action RecognitiononSomething-Something V2
Top-5 Accuracy· uses extra data· 2020-07-20
89.4
best: 96.3 (DejaVid)
MotionSqueeze: Neural Motion Feature Learning for Video Understanding arXiv:2007.09933

Computer Vision1 result

VideoonKinetics-400
Acc@1· 2020-07-20
76.4
best: 93.6 (OmniVec2)
MotionSqueeze: Neural Motion Feature Learning for Video Understanding arXiv:2007.09933