Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208795278> ?p ?o ?g. }
- W3208795278 abstract "Scene text detection remains a grand challenge due to the variation in text curvatures, orientations, and aspect ratios. One of the hardest problems in this task is how to represent text instances of arbitrary shapes. Although many methods have been proposed to model irregular texts in a flexible manner, most of them lose simplicity and robustness. Their complicated post-processings and the regression under Dirac delta distribution undermine the detection performance and the generalization ability. In this paper, we propose an efficient text instance representation named CentripetalText (CT), which decomposes text instances into the combination of text kernels and centripetal shifts. Specifically, we utilize the centripetal shifts to implement pixel aggregation, guiding the external text pixels to the internal text kernels. The relaxation operation is integrated into the dense regression for centripetal shifts, allowing the correct prediction in a range instead of a specific value. The convenient reconstruction of text contours and the tolerance of prediction errors in our method guarantee the high detection accuracy and the fast inference speed, respectively. Besides, we shrink our text detector into a proposal generation module, namely CentripetalText Proposal Network, replacing Segmentation Proposal Network in Mask TextSpotter v3 and producing more accurate proposals. To validate the effectiveness of our method, we conduct experiments on several commonly used scene text benchmarks, including both curved and multi-oriented text datasets. For the task of scene text detection, our approach achieves superior or competitive performance compared to other existing methods, e.g., F-measure of 86.3% at 40.0 FPS on Total-Text, F-measure of 86.1% at 34.8 FPS on MSRA-TD500, etc. For the task of end-to-end scene text recognition, our method outperforms Mask TextSpotter v3 by 1.1% on Total-Text." @default.
- W3208795278 created "2021-11-08" @default.
- W3208795278 creator A5010479652 @default.
- W3208795278 creator A5062931526 @default.
- W3208795278 creator A5063600625 @default.
- W3208795278 date "2021-07-13" @default.
- W3208795278 modified "2023-09-25" @default.
- W3208795278 title "CentripetalText: An Efficient Text Instance Representation for Scene Text Detection" @default.
- W3208795278 cites W1536680647 @default.
- W3208795278 cites W1903029394 @default.
- W3208795278 cites W1972065312 @default.
- W3208795278 cites W1988461287 @default.
- W3208795278 cites W2008806374 @default.
- W3208795278 cites W2074849287 @default.
- W3208795278 cites W2108598243 @default.
- W3208795278 cites W2144554289 @default.
- W3208795278 cites W2194775991 @default.
- W3208795278 cites W2343052201 @default.
- W3208795278 cites W2519818067 @default.
- W3208795278 cites W2560023338 @default.
- W3208795278 cites W2565639579 @default.
- W3208795278 cites W2605076167 @default.
- W3208795278 cites W2613718673 @default.
- W3208795278 cites W2772800855 @default.
- W3208795278 cites W2784050770 @default.
- W3208795278 cites W2810028092 @default.
- W3208795278 cites W2875814315 @default.
- W3208795278 cites W2886934227 @default.
- W3208795278 cites W2902494497 @default.
- W3208795278 cites W2962721361 @default.
- W3208795278 cites W2962773189 @default.
- W3208795278 cites W2962810613 @default.
- W3208795278 cites W2962914239 @default.
- W3208795278 cites W2963161243 @default.
- W3208795278 cites W2963299604 @default.
- W3208795278 cites W2963353821 @default.
- W3208795278 cites W2963398399 @default.
- W3208795278 cites W2963516811 @default.
- W3208795278 cites W2963647456 @default.
- W3208795278 cites W2964294787 @default.
- W3208795278 cites W2964685115 @default.
- W3208795278 cites W2967615747 @default.
- W3208795278 cites W2970910956 @default.
- W3208795278 cites W2981969038 @default.
- W3208795278 cites W2983626510 @default.
- W3208795278 cites W2991626090 @default.
- W3208795278 cites W2997371611 @default.
- W3208795278 cites W2998621280 @default.
- W3208795278 cites W3034514377 @default.
- W3208795278 cites W3034792612 @default.
- W3208795278 cites W3035679705 @default.
- W3208795278 cites W3102710196 @default.
- W3208795278 cites W3106228955 @default.
- W3208795278 cites W3106250896 @default.
- W3208795278 cites W3110398855 @default.
- W3208795278 hasPublicationYear "2021" @default.
- W3208795278 type Work @default.
- W3208795278 sameAs 3208795278 @default.
- W3208795278 citedByCount "0" @default.
- W3208795278 crossrefType "posted-content" @default.
- W3208795278 hasAuthorship W3208795278A5010479652 @default.
- W3208795278 hasAuthorship W3208795278A5062931526 @default.
- W3208795278 hasAuthorship W3208795278A5063600625 @default.
- W3208795278 hasConcept C104317684 @default.
- W3208795278 hasConcept C13280743 @default.
- W3208795278 hasConcept C153180895 @default.
- W3208795278 hasConcept C154945302 @default.
- W3208795278 hasConcept C160633673 @default.
- W3208795278 hasConcept C17744445 @default.
- W3208795278 hasConcept C185592680 @default.
- W3208795278 hasConcept C185798385 @default.
- W3208795278 hasConcept C199539241 @default.
- W3208795278 hasConcept C205649164 @default.
- W3208795278 hasConcept C2776214188 @default.
- W3208795278 hasConcept C2776359362 @default.
- W3208795278 hasConcept C41008148 @default.
- W3208795278 hasConcept C55493867 @default.
- W3208795278 hasConcept C63479239 @default.
- W3208795278 hasConcept C89600930 @default.
- W3208795278 hasConcept C94625758 @default.
- W3208795278 hasConceptScore W3208795278C104317684 @default.
- W3208795278 hasConceptScore W3208795278C13280743 @default.
- W3208795278 hasConceptScore W3208795278C153180895 @default.
- W3208795278 hasConceptScore W3208795278C154945302 @default.
- W3208795278 hasConceptScore W3208795278C160633673 @default.
- W3208795278 hasConceptScore W3208795278C17744445 @default.
- W3208795278 hasConceptScore W3208795278C185592680 @default.
- W3208795278 hasConceptScore W3208795278C185798385 @default.
- W3208795278 hasConceptScore W3208795278C199539241 @default.
- W3208795278 hasConceptScore W3208795278C205649164 @default.
- W3208795278 hasConceptScore W3208795278C2776214188 @default.
- W3208795278 hasConceptScore W3208795278C2776359362 @default.
- W3208795278 hasConceptScore W3208795278C41008148 @default.
- W3208795278 hasConceptScore W3208795278C55493867 @default.
- W3208795278 hasConceptScore W3208795278C63479239 @default.
- W3208795278 hasConceptScore W3208795278C89600930 @default.
- W3208795278 hasConceptScore W3208795278C94625758 @default.
- W3208795278 hasOpenAccess W3208795278 @default.
- W3208795278 hasRelatedWork W10096406 @default.
- W3208795278 hasRelatedWork W13637491 @default.