Matches in SemOpenAlex for { <https://semopenalex.org/work/W2922690896> ?p ?o ?g. }
- W2922690896 abstract "Scene text detection, an essential step of scene text recognition system, is to locate text instances in natural scene images automatically. Some recent attempts benefiting from Mask R-CNN formulate scene text detection task as an instance segmentation problem and achieve remarkable performance. In this paper, we present a new Mask R-CNN based framework named Pyramid Mask Text Detector (PMTD) to handle the scene text detection. Instead of binary text mask generated by the existing Mask R-CNN based methods, our PMTD performs pixel-level regression under the guidance of location-aware supervision, yielding a more informative soft text mask for each text instance. As for the generation of text boxes, PMTD reinterprets the obtained 2D soft mask into 3D space and introduces a novel plane clustering algorithm to derive the optimal text box on the basis of 3D shape. Experiments on standard datasets demonstrate that the proposed PMTD brings consistent and noticeable gain and clearly outperforms state-of-the-art methods. Specifically, it achieves an F-measure of 80.13% on ICDAR 2017 MLT dataset." @default.
- W2922690896 created "2019-04-01" @default.
- W2922690896 creator A5022526821 @default.
- W2922690896 creator A5026443043 @default.
- W2922690896 creator A5029551526 @default.
- W2922690896 creator A5056847110 @default.
- W2922690896 creator A5064562203 @default.
- W2922690896 creator A5074700770 @default.
- W2922690896 date "2019-03-28" @default.
- W2922690896 modified "2023-10-18" @default.
- W2922690896 title "Pyramid Mask Text Detector" @default.
- W2922690896 cites W117491841 @default.
- W2922690896 cites W1903029394 @default.
- W2922690896 cites W1922126009 @default.
- W2922690896 cites W2008806374 @default.
- W2922690896 cites W2050551672 @default.
- W2922690896 cites W2108598243 @default.
- W2922690896 cites W2135231474 @default.
- W2922690896 cites W2144554289 @default.
- W2922690896 cites W2194775991 @default.
- W2922690896 cites W2343052201 @default.
- W2922690896 cites W2519818067 @default.
- W2922690896 cites W2535388113 @default.
- W2922690896 cites W2599765304 @default.
- W2922690896 cites W2604735854 @default.
- W2922690896 cites W2605076167 @default.
- W2922690896 cites W2605982830 @default.
- W2922690896 cites W2613718673 @default.
- W2922690896 cites W2725486421 @default.
- W2922690896 cites W2772800855 @default.
- W2922690896 cites W2785383245 @default.
- W2922690896 cites W2798591388 @default.
- W2922690896 cites W2798957492 @default.
- W2922690896 cites W2806327167 @default.
- W2922690896 cites W2810028092 @default.
- W2922690896 cites W2875814315 @default.
- W2922690896 cites W2900703600 @default.
- W2922690896 cites W2901776468 @default.
- W2922690896 cites W2901862516 @default.
- W2922690896 cites W2962773189 @default.
- W2922690896 cites W2962804639 @default.
- W2922690896 cites W2962810613 @default.
- W2922690896 cites W2962986948 @default.
- W2922690896 cites W2963037989 @default.
- W2922690896 cites W2963187132 @default.
- W2922690896 cites W2963299604 @default.
- W2922690896 cites W2963836589 @default.
- W2922690896 cites W2963840241 @default.
- W2922690896 cites W2963977642 @default.
- W2922690896 cites W2964018263 @default.
- W2922690896 cites W3106228955 @default.
- W2922690896 cites W3106250896 @default.
- W2922690896 cites W654550266 @default.
- W2922690896 cites W70975097 @default.
- W2922690896 cites W97978472 @default.
- W2922690896 hasPublicationYear "2019" @default.
- W2922690896 type Work @default.
- W2922690896 sameAs 2922690896 @default.
- W2922690896 citedByCount "16" @default.
- W2922690896 countsByYear W29226908962019 @default.
- W2922690896 countsByYear W29226908962020 @default.
- W2922690896 countsByYear W29226908962021 @default.
- W2922690896 countsByYear W29226908962022 @default.
- W2922690896 crossrefType "posted-content" @default.
- W2922690896 hasAuthorship W2922690896A5022526821 @default.
- W2922690896 hasAuthorship W2922690896A5026443043 @default.
- W2922690896 hasAuthorship W2922690896A5029551526 @default.
- W2922690896 hasAuthorship W2922690896A5056847110 @default.
- W2922690896 hasAuthorship W2922690896A5064562203 @default.
- W2922690896 hasAuthorship W2922690896A5074700770 @default.
- W2922690896 hasConcept C115961682 @default.
- W2922690896 hasConcept C124101348 @default.
- W2922690896 hasConcept C142575187 @default.
- W2922690896 hasConcept C153180895 @default.
- W2922690896 hasConcept C154945302 @default.
- W2922690896 hasConcept C160633673 @default.
- W2922690896 hasConcept C2524010 @default.
- W2922690896 hasConcept C2780009758 @default.
- W2922690896 hasConcept C2983589003 @default.
- W2922690896 hasConcept C31972630 @default.
- W2922690896 hasConcept C33923547 @default.
- W2922690896 hasConcept C41008148 @default.
- W2922690896 hasConcept C48372109 @default.
- W2922690896 hasConcept C73555534 @default.
- W2922690896 hasConcept C76155785 @default.
- W2922690896 hasConcept C89600930 @default.
- W2922690896 hasConcept C94375191 @default.
- W2922690896 hasConcept C94915269 @default.
- W2922690896 hasConceptScore W2922690896C115961682 @default.
- W2922690896 hasConceptScore W2922690896C124101348 @default.
- W2922690896 hasConceptScore W2922690896C142575187 @default.
- W2922690896 hasConceptScore W2922690896C153180895 @default.
- W2922690896 hasConceptScore W2922690896C154945302 @default.
- W2922690896 hasConceptScore W2922690896C160633673 @default.
- W2922690896 hasConceptScore W2922690896C2524010 @default.
- W2922690896 hasConceptScore W2922690896C2780009758 @default.
- W2922690896 hasConceptScore W2922690896C2983589003 @default.
- W2922690896 hasConceptScore W2922690896C31972630 @default.
- W2922690896 hasConceptScore W2922690896C33923547 @default.
- W2922690896 hasConceptScore W2922690896C41008148 @default.