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/CLIP4STR-B

CLIP4STR-B

Reported on 33 benchmarks across 3 tasks · 1 paper

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

Computer Vision22 results

Scene ParsingonSVT
Accuracy· uses extra data· 2023-05-23
98.3
best: 99.1 (CLIP4STR-H (DFN-5B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene ParsingonSVTP
Accuracy· uses extra data· 2023-05-23
97.2
best: 98.6 (DTrOCR 105M)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene ParsingonCUTE80
Accuracy· uses extra data· 2023-05-23
99.3
best: 99.7 (CPPD)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene ParsingonUber-Text
Accuracy (%)· uses extra data· 2023-05-23
86.8
best: 92.2 (CLIP4STR-L (DataComp-1B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene ParsingonWOST
1:1 Accuracy· uses extra data· 2023-05-23
87
best: 90.9 (CLIP4STR-H (DFN-5B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene ParsingonCOCO-Text
1:1 Accuracy· uses extra data· 2023-05-23
81.1
best: 81.9 (CLIP4STR-L)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene ParsingonHOST
1:1 Accuracy· uses extra data· 2023-05-23
79.8
best: 82.7 (CLIP4STR-L)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene ParsingonIC19-Art
Accuracy (%)· uses extra data· 2023-05-23
85.8
best: 86.4 (CLIP4STR-L (DataComp-1B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene ParsingonICDAR2015
Accuracy· uses extra data· 2023-05-23
90.6
best: 93.5 (DTrOCR 105M)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene ParsingonIIIT5k
Accuracy· uses extra data· 2023-05-23
99.2
best: 99.6 (CLIP4STR-L (DataComp-1B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene ParsingonICDAR2013
Accuracy· uses extra data· 2023-05-23
98.3
best: 99.42 (CLIP4STR-L*)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene Text RecognitiononSVT
Accuracy· uses extra data· 2023-05-23
98.3
best: 99.1 (CLIP4STR-H (DFN-5B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene Text RecognitiononSVTP
Accuracy· uses extra data· 2023-05-23
97.2
best: 98.6 (DTrOCR 105M)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene Text RecognitiononCUTE80
Accuracy· uses extra data· 2023-05-23
99.3
best: 99.7 (CPPD)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene Text RecognitiononUber-Text
Accuracy (%)· uses extra data· 2023-05-23
86.8
best: 92.2 (CLIP4STR-L (DataComp-1B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene Text RecognitiononWOST
1:1 Accuracy· uses extra data· 2023-05-23
87
best: 90.9 (CLIP4STR-H (DFN-5B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene Text RecognitiononCOCO-Text
1:1 Accuracy· uses extra data· 2023-05-23
81.1
best: 81.9 (CLIP4STR-L)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene Text RecognitiononHOST
1:1 Accuracy· uses extra data· 2023-05-23
79.8
best: 82.7 (CLIP4STR-L)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene Text RecognitiononIC19-Art
Accuracy (%)· uses extra data· 2023-05-23
85.8
best: 86.4 (CLIP4STR-L (DataComp-1B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene Text RecognitiononICDAR2015
Accuracy· uses extra data· 2023-05-23
90.6
best: 93.5 (DTrOCR 105M)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene Text RecognitiononIIIT5k
Accuracy· uses extra data· 2023-05-23
99.2
best: 99.6 (CLIP4STR-L (DataComp-1B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene Text RecognitiononICDAR2013
Accuracy· uses extra data· 2023-05-23
98.3
best: 99.42 (CLIP4STR-L*)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014

Audio11 results

2D Semantic SegmentationonSVT
Accuracy· uses extra data· 2023-05-23
98.3
best: 99.1 (CLIP4STR-H (DFN-5B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
2D Semantic SegmentationonSVTP
Accuracy· uses extra data· 2023-05-23
97.2
best: 98.6 (DTrOCR 105M)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
2D Semantic SegmentationonCUTE80
Accuracy· uses extra data· 2023-05-23
99.3
best: 99.7 (CPPD)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
2D Semantic SegmentationonUber-Text
Accuracy (%)· uses extra data· 2023-05-23
86.8
best: 92.2 (CLIP4STR-L (DataComp-1B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
2D Semantic SegmentationonWOST
1:1 Accuracy· uses extra data· 2023-05-23
87
best: 90.9 (CLIP4STR-H (DFN-5B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
2D Semantic SegmentationonCOCO-Text
1:1 Accuracy· uses extra data· 2023-05-23
81.1
best: 81.9 (CLIP4STR-L)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
2D Semantic SegmentationonHOST
1:1 Accuracy· uses extra data· 2023-05-23
79.8
best: 82.7 (CLIP4STR-L)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
2D Semantic SegmentationonIC19-Art
Accuracy (%)· uses extra data· 2023-05-23
85.8
best: 86.4 (CLIP4STR-L (DataComp-1B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
2D Semantic SegmentationonICDAR2015
Accuracy· uses extra data· 2023-05-23
90.6
best: 93.5 (DTrOCR 105M)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
2D Semantic SegmentationonIIIT5k
Accuracy· uses extra data· 2023-05-23
99.2
best: 99.6 (CLIP4STR-L (DataComp-1B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
2D Semantic SegmentationonICDAR2013
Accuracy· uses extra data· 2023-05-23
98.3
best: 99.42 (CLIP4STR-L*)
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014