FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2902494497> ?p ?o ?g. }

• W2902494497 endingPage "5579" @default.
• W2902494497 startingPage "5566" @default.
• W2902494497 abstract "Scene text detection is an important step of scene text reading system. The main challenges lie on significantly varied sizes and aspect ratios, arbitrary orientations and shapes. Driven by recent progress in deep learning, impressive performances have been achieved for multi-oriented text detection. Yet, the performance drops dramatically in detecting curved texts due to the limited text representation (e.g., horizontal bounding boxes, rotated rectangles, or quadrilaterals). It is of great interest to detect curved texts, which are actually very common in natural scenes. In this paper, we present a novel text detector named TextField for detecting irregular scene texts. Specifically, we learn a direction field pointing away from the nearest text boundary to each text point. This direction field is represented by an image of two-dimensional vectors and learned via a fully convolutional neural network. It encodes both binary text mask and direction information used to separate adjacent text instances, which is challenging for classical segmentation-based approaches. Based on the learned direction field, we apply a simple yet effective morphological-based post-processing to achieve the final detection. Experimental results show that the proposed TextField outperforms the state-of-the-art methods by a large margin (28% and 8%) on two curved text datasets: Total-Text and CTW1500, respectively, and also achieves very competitive performance on multi-oriented datasets: ICDAR 2015 and MSRA-TD500. Furthermore, TextField is robust in generalizing to unseen datasets. The code is available at https://github.com/YukangWang/TextField." @default.
• W2902494497 created "2018-12-11" @default.
• W2902494497 creator A5001786727 @default.
• W2902494497 creator A5004350258 @default.
• W2902494497 creator A5025049641 @default.
• W2902494497 creator A5039363991 @default.
• W2902494497 creator A5068347202 @default.
• W2902494497 creator A5082564408 @default.
• W2902494497 date "2019-11-01" @default.
• W2902494497 modified "2023-10-17" @default.
• W2902494497 title "TextField: Learning a Deep Direction Field for Irregular Scene Text Detection" @default.
• W2902494497 cites W117491841 @default.
• W2902494497 cites W1521064364 @default.
• W2902494497 cites W1745334888 @default.
• W2902494497 cites W1903029394 @default.
• W2902494497 cites W1922126009 @default.
• W2902494497 cites W1966693245 @default.
• W2902494497 cites W1966828720 @default.
• W2902494497 cites W1967140047 @default.
• W2902494497 cites W1988461287 @default.
• W2902494497 cites W1999284580 @default.
• W2902494497 cites W2001999290 @default.
• W2902494497 cites W2013360608 @default.
• W2902494497 cites W2019478948 @default.
• W2902494497 cites W2061802763 @default.
• W2902494497 cites W2099096599 @default.
• W2902494497 cites W2108598243 @default.
• W2902494497 cites W2124404372 @default.
• W2902494497 cites W2128854450 @default.
• W2902494497 cites W2131163834 @default.
• W2902494497 cites W2135231474 @default.
• W2902494497 cites W2142159465 @default.
• W2902494497 cites W2144554289 @default.
• W2902494497 cites W2146842130 @default.
• W2902494497 cites W2155893237 @default.
• W2902494497 cites W2194187530 @default.
• W2902494497 cites W2217433794 @default.
• W2902494497 cites W2239285313 @default.
• W2902494497 cites W2294834600 @default.
• W2902494497 cites W2339589954 @default.
• W2902494497 cites W2343052201 @default.
• W2902494497 cites W2396529792 @default.
• W2902494497 cites W2519321174 @default.
• W2902494497 cites W2519818067 @default.
• W2902494497 cites W2557889580 @default.
• W2902494497 cites W2604243686 @default.
• W2902494497 cites W2604735854 @default.
• W2902494497 cites W2605076167 @default.
• W2902494497 cites W2605982830 @default.
• W2902494497 cites W2735220054 @default.
• W2902494497 cites W2740819638 @default.
• W2902494497 cites W2776766448 @default.
• W2902494497 cites W2779757316 @default.
• W2902494497 cites W2784050770 @default.
• W2902494497 cites W2798450692 @default.
• W2902494497 cites W2831607544 @default.
• W2902494497 cites W2873558679 @default.
• W2902494497 cites W2962804639 @default.
• W2902494497 cites W2962935569 @default.
• W2902494497 cites W2962986948 @default.
• W2902494497 cites W2963037989 @default.
• W2902494497 cites W2963161243 @default.
• W2902494497 cites W2963516811 @default.
• W2902494497 cites W2963840241 @default.
• W2902494497 cites W2963977642 @default.
• W2902494497 cites W2964236837 @default.
• W2902494497 cites W2964294787 @default.
• W2902494497 cites W3106228955 @default.
• W2902494497 cites W639708223 @default.
• W2902494497 cites W654550266 @default.
• W2902494497 doi "https://doi.org/10.1109/tip.2019.2900589" @default.
• W2902494497 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30802859" @default.
• W2902494497 hasPublicationYear "2019" @default.
• W2902494497 type Work @default.
• W2902494497 sameAs 2902494497 @default.
• W2902494497 citedByCount "233" @default.
• W2902494497 countsByYear W29024944972019 @default.
• W2902494497 countsByYear W29024944972020 @default.
• W2902494497 countsByYear W29024944972021 @default.
• W2902494497 countsByYear W29024944972022 @default.
• W2902494497 countsByYear W29024944972023 @default.
• W2902494497 crossrefType "journal-article" @default.
• W2902494497 hasAuthorship W2902494497A5001786727 @default.
• W2902494497 hasAuthorship W2902494497A5004350258 @default.
• W2902494497 hasAuthorship W2902494497A5025049641 @default.
• W2902494497 hasAuthorship W2902494497A5039363991 @default.
• W2902494497 hasAuthorship W2902494497A5068347202 @default.
• W2902494497 hasAuthorship W2902494497A5082564408 @default.
• W2902494497 hasBestOaLocation W29024944972 @default.
• W2902494497 hasConcept C108583219 @default.
• W2902494497 hasConcept C115961682 @default.
• W2902494497 hasConcept C119857082 @default.
• W2902494497 hasConcept C127413603 @default.
• W2902494497 hasConcept C134306372 @default.
• W2902494497 hasConcept C146978453 @default.
• W2902494497 hasConcept C147037132 @default.
• W2902494497 hasConcept C153180895 @default.
• W2902494497 hasConcept C154945302 @default.

• next