Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293519394> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4293519394 abstract "Many state-of-the-art scene text recognition methods leverage a pre-designed backbone for general object recognition, where general objects are usually lacking of distinctive characteristics. However, unlike general objects, texts in images are usually composed of narrow strokes and their characters often share similar attributes, e.g. texture and intensity. Such useful patterns can be deteriorated if directly employing standard convolutional networks to the scene text recognition. To solve the problem, we introduce a novel operation Strip Convolution, a specially designed convolution for extracting features of narrow strokes. And we further apply a Hierarchical Correlation strategy, adopting multi-level attention mechanisms to capture common text attributes. Based on this, we design a novel framework, named as Hierarchical Correlated Strip Convolutonal network for scene text recognition. Extensive experiments demonstrate the superiority of the proposed HCSC network, improving the accuracy of text recognition effectively." @default.
- W4293519394 created "2022-08-30" @default.
- W4293519394 creator A5010954205 @default.
- W4293519394 creator A5022256556 @default.
- W4293519394 date "2022-07-18" @default.
- W4293519394 modified "2023-10-16" @default.
- W4293519394 title "Pattern Matters: Hierarchical Correlated Strip Convolutional Network for Scene Text Recognition" @default.
- W4293519394 cites W2194187530 @default.
- W4293519394 cites W2288122362 @default.
- W4293519394 cites W2294053032 @default.
- W4293519394 cites W2593572697 @default.
- W4293519394 cites W2740767790 @default.
- W4293519394 cites W2750938222 @default.
- W4293519394 cites W2780740184 @default.
- W4293519394 cites W2795619303 @default.
- W4293519394 cites W2894730515 @default.
- W4293519394 cites W2955058313 @default.
- W4293519394 cites W2959965583 @default.
- W4293519394 cites W2963233387 @default.
- W4293519394 cites W2963299454 @default.
- W4293519394 cites W2963327605 @default.
- W4293519394 cites W2963517393 @default.
- W4293519394 cites W2963712589 @default.
- W4293519394 cites W2965066169 @default.
- W4293519394 cites W2983626510 @default.
- W4293519394 cites W3004846386 @default.
- W4293519394 doi "https://doi.org/10.1109/icme52920.2022.9860006" @default.
- W4293519394 hasPublicationYear "2022" @default.
- W4293519394 type Work @default.
- W4293519394 citedByCount "0" @default.
- W4293519394 crossrefType "proceedings-article" @default.
- W4293519394 hasAuthorship W4293519394A5010954205 @default.
- W4293519394 hasAuthorship W4293519394A5022256556 @default.
- W4293519394 hasConcept C153083717 @default.
- W4293519394 hasConcept C153180895 @default.
- W4293519394 hasConcept C154945302 @default.
- W4293519394 hasConcept C2781238097 @default.
- W4293519394 hasConcept C41008148 @default.
- W4293519394 hasConcept C45347329 @default.
- W4293519394 hasConcept C50644808 @default.
- W4293519394 hasConcept C64876066 @default.
- W4293519394 hasConcept C81363708 @default.
- W4293519394 hasConceptScore W4293519394C153083717 @default.
- W4293519394 hasConceptScore W4293519394C153180895 @default.
- W4293519394 hasConceptScore W4293519394C154945302 @default.
- W4293519394 hasConceptScore W4293519394C2781238097 @default.
- W4293519394 hasConceptScore W4293519394C41008148 @default.
- W4293519394 hasConceptScore W4293519394C45347329 @default.
- W4293519394 hasConceptScore W4293519394C50644808 @default.
- W4293519394 hasConceptScore W4293519394C64876066 @default.
- W4293519394 hasConceptScore W4293519394C81363708 @default.
- W4293519394 hasLocation W42935193941 @default.
- W4293519394 hasOpenAccess W4293519394 @default.
- W4293519394 hasPrimaryLocation W42935193941 @default.
- W4293519394 hasRelatedWork W1528044252 @default.
- W4293519394 hasRelatedWork W1531683208 @default.
- W4293519394 hasRelatedWork W1569815043 @default.
- W4293519394 hasRelatedWork W2009052148 @default.
- W4293519394 hasRelatedWork W2157418942 @default.
- W4293519394 hasRelatedWork W2163529784 @default.
- W4293519394 hasRelatedWork W2328068029 @default.
- W4293519394 hasRelatedWork W2363840281 @default.
- W4293519394 hasRelatedWork W2372904789 @default.
- W4293519394 hasRelatedWork W2613077666 @default.
- W4293519394 isParatext "false" @default.
- W4293519394 isRetracted "false" @default.
- W4293519394 workType "article" @default.