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/SlowFast

SlowFast

Reported on 12 benchmarks across 2 tasks · 4 papers · 6 SOTA

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

Robots6 results

Activity RecognitiononMECCANO
Top-1 Accuracy· 2020-10-12
42.85
SOTA
The MECCANO Dataset: Understanding Human-Object Interactions from Egocentric Videos in an Industrial-like Domain arXiv:2010.05654
Activity RecognitiononDiving-48
Accuracy· 2018-12-10
77.6
best: 94.9 (LVMAE)
SOTA
SlowFast Networks for Video Recognition arXiv:1812.03982
Activity RecognitiononH2O (2 Hands and Objects)
Actions Top-1· 2018-12-10
77.69
best: 93.39 (HandFormer-B/21x8)
SOTA
SlowFast Networks for Video Recognition arXiv:1812.03982
Activity RecognitiononHAA500
Top-1 (%)· 2020-09-11
39.93
best: 64.4 (TSN)
HAA500: Human-Centric Atomic Action Dataset with Curated Videos arXiv:2009.05224
Activity RecognitiononEPIC-KITCHENS-100
Action@1· 2020-06-23
36.81
best: 58.3 (LLaVAction)
Rescaling Egocentric Vision arXiv:2006.13256
Activity RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2018-12-10
61.7
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
SlowFast Networks for Video Recognition arXiv:1812.03982

Time Series6 results

Action RecognitiononMECCANO
Top-1 Accuracy· 2020-10-12
42.85
SOTA
The MECCANO Dataset: Understanding Human-Object Interactions from Egocentric Videos in an Industrial-like Domain arXiv:2010.05654
Action RecognitiononDiving-48
Accuracy· 2018-12-10
77.6
best: 94.9 (LVMAE)
SOTA
SlowFast Networks for Video Recognition arXiv:1812.03982
Action RecognitiononH2O (2 Hands and Objects)
Actions Top-1· 2018-12-10
77.69
best: 93.39 (HandFormer-B/21x8)
SOTA
SlowFast Networks for Video Recognition arXiv:1812.03982
Action RecognitiononHAA500
Top-1 (%)· 2020-09-11
39.93
best: 64.4 (TSN)
HAA500: Human-Centric Atomic Action Dataset with Curated Videos arXiv:2009.05224
Action RecognitiononEPIC-KITCHENS-100
Action@1· 2020-06-23
36.81
best: 58.3 (LLaVAction)
Rescaling Egocentric Vision arXiv:2006.13256
Action RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2018-12-10
61.7
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
SlowFast Networks for Video Recognition arXiv:1812.03982