VideoMAE V2

Reported on 3 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.

Robots1 result

Activity RecognitiononAVA v2.2
mAP (Val)· 2023-03-29
18.24
best: 20.2 (YOWO+LFB*)
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727

Time Series1 result

Action RecognitiononAVA v2.2
mAP (Val)· 2023-03-29
18.24
best: 20.2 (YOWO+LFB*)
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727

Computer Vision1 result

Action Recognition In VideosonAVA v2.2
mAP (Val)· 2023-03-29
18.24
best: 20.2 (YOWO+LFB*)
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727