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/MATRN

MATRN

Reported on 18 benchmarks across 3 tasks · 1 paper · 18 SOTA

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

Computer Vision12 results

Scene ParsingonSVT
Accuracy· 2021-11-30
95
best: 99.1 (CLIP4STR-H (DFN-5B))
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263
Scene ParsingonSVTP
Accuracy· 2021-11-30
90.6
best: 98.6 (DTrOCR 105M)
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263
Scene ParsingonCUTE80
Accuracy· 2021-11-30
93.5
best: 99.7 (CPPD)
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263
Scene ParsingonICDAR2015
Accuracy· 2021-11-30
86.6
best: 93.5 (DTrOCR 105M)
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263
Scene ParsingonIIIT5k
Accuracy· 2021-11-30
96.6
best: 99.6 (CLIP4STR-L (DataComp-1B))
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263
Scene ParsingonICDAR2013
Accuracy· 2021-11-30
97.9
best: 99.42 (CLIP4STR-L*)
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263
Scene Text RecognitiononSVT
Accuracy· 2021-11-30
95
best: 99.1 (CLIP4STR-H (DFN-5B))
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263
Scene Text RecognitiononSVTP
Accuracy· 2021-11-30
90.6
best: 98.6 (DTrOCR 105M)
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263
Scene Text RecognitiononCUTE80
Accuracy· 2021-11-30
93.5
best: 99.7 (CPPD)
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263
Scene Text RecognitiononICDAR2015
Accuracy· 2021-11-30
86.6
best: 93.5 (DTrOCR 105M)
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263
Scene Text RecognitiononIIIT5k
Accuracy· 2021-11-30
96.6
best: 99.6 (CLIP4STR-L (DataComp-1B))
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263
Scene Text RecognitiononICDAR2013
Accuracy· 2021-11-30
97.9
best: 99.42 (CLIP4STR-L*)
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263

Audio6 results

2D Semantic SegmentationonSVT
Accuracy· 2021-11-30
95
best: 99.1 (CLIP4STR-H (DFN-5B))
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263
2D Semantic SegmentationonSVTP
Accuracy· 2021-11-30
90.6
best: 98.6 (DTrOCR 105M)
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263
2D Semantic SegmentationonCUTE80
Accuracy· 2021-11-30
93.5
best: 99.7 (CPPD)
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263
2D Semantic SegmentationonICDAR2015
Accuracy· 2021-11-30
86.6
best: 93.5 (DTrOCR 105M)
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263
2D Semantic SegmentationonIIIT5k
Accuracy· 2021-11-30
96.6
best: 99.6 (CLIP4STR-L (DataComp-1B))
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263
2D Semantic SegmentationonICDAR2013
Accuracy· 2021-11-30
97.9
best: 99.42 (CLIP4STR-L*)
SOTA
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features arXiv:2111.15263