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/ViViT-L/16x2 Fact. encoder

ViViT-L/16x2 Fact. encoder

Reported on 10 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.

Robots5 results

Activity RecognitiononEPIC-KITCHENS-100
Action@1· 2021-03-29
44
best: 58.3 (LLaVAction)
ViViT: A Video Vision Transformer arXiv:2103.15691
Activity RecognitiononEPIC-KITCHENS-100
Noun@1· 2021-03-29
56.8
best: 69 (LLaVAction)
ViViT: A Video Vision Transformer arXiv:2103.15691
Activity RecognitiononEPIC-KITCHENS-100
Verb@1· 2021-03-29
66.4
best: 76.2 (TIM)
ViViT: A Video Vision Transformer arXiv:2103.15691
Activity RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2021-03-29
65.4
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
ViViT: A Video Vision Transformer arXiv:2103.15691
Activity RecognitiononSomething-Something V2
Top-5 Accuracy· uses extra data· 2021-03-29
89.8
best: 96.3 (DejaVid)
ViViT: A Video Vision Transformer arXiv:2103.15691

Time Series5 results

Action RecognitiononEPIC-KITCHENS-100
Action@1· 2021-03-29
44
best: 58.3 (LLaVAction)
ViViT: A Video Vision Transformer arXiv:2103.15691
Action RecognitiononEPIC-KITCHENS-100
Noun@1· 2021-03-29
56.8
best: 69 (LLaVAction)
ViViT: A Video Vision Transformer arXiv:2103.15691
Action RecognitiononEPIC-KITCHENS-100
Verb@1· 2021-03-29
66.4
best: 76.2 (TIM)
ViViT: A Video Vision Transformer arXiv:2103.15691
Action RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2021-03-29
65.4
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
ViViT: A Video Vision Transformer arXiv:2103.15691
Action RecognitiononSomething-Something V2
Top-5 Accuracy· uses extra data· 2021-03-29
89.8
best: 96.3 (DejaVid)
ViViT: A Video Vision Transformer arXiv:2103.15691