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/VideoMAE (no extra data, ViT-B, 16frame)

VideoMAE (no extra data, ViT-B, 16frame)

Reported on 6 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.

Robots3 results

Activity RecognitiononSomething-Something V2
Parameters· 2022-03-23
87
best: 2131 (InternVideo2-6B)
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training arXiv:2203.12602
Activity RecognitiononSomething-Something V2
Top-1 Accuracy· 2022-03-23
70.8
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training arXiv:2203.12602
Activity RecognitiononSomething-Something V2
Top-5 Accuracy· 2022-03-23
92.4
best: 96.3 (DejaVid)
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training arXiv:2203.12602

Time Series3 results

Action RecognitiononSomething-Something V2
Parameters· 2022-03-23
87
best: 2131 (InternVideo2-6B)
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training arXiv:2203.12602
Action RecognitiononSomething-Something V2
Top-1 Accuracy· 2022-03-23
70.8
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training arXiv:2203.12602
Action RecognitiononSomething-Something V2
Top-5 Accuracy· 2022-03-23
92.4
best: 96.3 (DejaVid)
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training arXiv:2203.12602