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/STRM

STRM

Reported on 8 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Robots4 results

Activity RecognitiononHMDB51
1:1 Accuracy· 2021-12-09
77.3
SOTA
Spatio-temporal Relation Modeling for Few-shot Action Recognition arXiv:2112.05132
Activity RecognitiononUCF101
1:1 Accuracy· uses extra data· 2021-12-09
96.8
SOTA
Spatio-temporal Relation Modeling for Few-shot Action Recognition arXiv:2112.05132
Activity RecognitiononSomething-Something-100
1:1 Accuracy· 2021-12-09
68.1
best: 69 (HyRSM)
SOTA
Spatio-temporal Relation Modeling for Few-shot Action Recognition arXiv:2112.05132
Activity RecognitiononKinetics-100
Accuracy· 2021-12-09
86.7
best: 94.7 (Name Tuning)
Spatio-temporal Relation Modeling for Few-shot Action Recognition arXiv:2112.05132

Time Series4 results

Action RecognitiononHMDB51
1:1 Accuracy· 2021-12-09
77.3
SOTA
Spatio-temporal Relation Modeling for Few-shot Action Recognition arXiv:2112.05132
Action RecognitiononUCF101
1:1 Accuracy· uses extra data· 2021-12-09
96.8
SOTA
Spatio-temporal Relation Modeling for Few-shot Action Recognition arXiv:2112.05132
Action RecognitiononSomething-Something-100
1:1 Accuracy· 2021-12-09
68.1
best: 69 (HyRSM)
SOTA
Spatio-temporal Relation Modeling for Few-shot Action Recognition arXiv:2112.05132
Action RecognitiononKinetics-100
Accuracy· 2021-12-09
86.7
best: 94.7 (Name Tuning)
Spatio-temporal Relation Modeling for Few-shot Action Recognition arXiv:2112.05132