Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891438060> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2891438060 abstract "Reading text in the wild is a challenging task in computer vision. Scene text suffers from various background noise, including shadow, irrelevant symbols and background texture. In order to reduce the disturbance of background noise, we propose a dense chained attention network with stacked attention modules for scene text recognition. Each attention module learns the attention map that is adapted to corresponding features to enhance the foreground text and suppress the background noise. Besides, the attention branch is designed with the convolution-deconvolution structure which rapidly captures global information to guide the discriminative feature selection. We stack multiple attention modules to gradually refine the attention maps and capture both the low-level appearance feature and the high-level semantic information. Extensive experiments on the standard benchmarks, the Street View Text, IIIT5K, and ICDAR datasets validate the superiority of the proposed method. The dense chained attention network achieves state-of-the-art or highly competitive recognition performance." @default.
- W2891438060 created "2018-09-27" @default.
- W2891438060 creator A5000205902 @default.
- W2891438060 creator A5009348332 @default.
- W2891438060 creator A5048295434 @default.
- W2891438060 creator A5058420913 @default.
- W2891438060 creator A5063778895 @default.
- W2891438060 date "2018-10-01" @default.
- W2891438060 modified "2023-10-11" @default.
- W2891438060 title "Dense Chained Attention Network for Scene Text Recognition" @default.
- W2891438060 cites W1677182931 @default.
- W2891438060 cites W1895191496 @default.
- W2891438060 cites W1922126009 @default.
- W2891438060 cites W1978729128 @default.
- W2891438060 cites W1981283549 @default.
- W2891438060 cites W1990550880 @default.
- W2891438060 cites W1998042868 @default.
- W2891438060 cites W2122221966 @default.
- W2891438060 cites W2127141656 @default.
- W2891438060 cites W2740767790 @default.
- W2891438060 cites W2750938222 @default.
- W2891438060 cites W2963446712 @default.
- W2891438060 cites W2963517393 @default.
- W2891438060 doi "https://doi.org/10.1109/icip.2018.8451273" @default.
- W2891438060 hasPublicationYear "2018" @default.
- W2891438060 type Work @default.
- W2891438060 sameAs 2891438060 @default.
- W2891438060 citedByCount "8" @default.
- W2891438060 countsByYear W28914380602019 @default.
- W2891438060 countsByYear W28914380602020 @default.
- W2891438060 countsByYear W28914380602021 @default.
- W2891438060 crossrefType "proceedings-article" @default.
- W2891438060 hasAuthorship W2891438060A5000205902 @default.
- W2891438060 hasAuthorship W2891438060A5009348332 @default.
- W2891438060 hasAuthorship W2891438060A5048295434 @default.
- W2891438060 hasAuthorship W2891438060A5058420913 @default.
- W2891438060 hasAuthorship W2891438060A5063778895 @default.
- W2891438060 hasConcept C11413529 @default.
- W2891438060 hasConcept C115961682 @default.
- W2891438060 hasConcept C138885662 @default.
- W2891438060 hasConcept C153180895 @default.
- W2891438060 hasConcept C154945302 @default.
- W2891438060 hasConcept C162324750 @default.
- W2891438060 hasConcept C174576160 @default.
- W2891438060 hasConcept C187736073 @default.
- W2891438060 hasConcept C2776401178 @default.
- W2891438060 hasConcept C2780451532 @default.
- W2891438060 hasConcept C31972630 @default.
- W2891438060 hasConcept C41008148 @default.
- W2891438060 hasConcept C41895202 @default.
- W2891438060 hasConcept C45347329 @default.
- W2891438060 hasConcept C50644808 @default.
- W2891438060 hasConcept C52622490 @default.
- W2891438060 hasConcept C81363708 @default.
- W2891438060 hasConcept C97931131 @default.
- W2891438060 hasConcept C99498987 @default.
- W2891438060 hasConceptScore W2891438060C11413529 @default.
- W2891438060 hasConceptScore W2891438060C115961682 @default.
- W2891438060 hasConceptScore W2891438060C138885662 @default.
- W2891438060 hasConceptScore W2891438060C153180895 @default.
- W2891438060 hasConceptScore W2891438060C154945302 @default.
- W2891438060 hasConceptScore W2891438060C162324750 @default.
- W2891438060 hasConceptScore W2891438060C174576160 @default.
- W2891438060 hasConceptScore W2891438060C187736073 @default.
- W2891438060 hasConceptScore W2891438060C2776401178 @default.
- W2891438060 hasConceptScore W2891438060C2780451532 @default.
- W2891438060 hasConceptScore W2891438060C31972630 @default.
- W2891438060 hasConceptScore W2891438060C41008148 @default.
- W2891438060 hasConceptScore W2891438060C41895202 @default.
- W2891438060 hasConceptScore W2891438060C45347329 @default.
- W2891438060 hasConceptScore W2891438060C50644808 @default.
- W2891438060 hasConceptScore W2891438060C52622490 @default.
- W2891438060 hasConceptScore W2891438060C81363708 @default.
- W2891438060 hasConceptScore W2891438060C97931131 @default.
- W2891438060 hasConceptScore W2891438060C99498987 @default.
- W2891438060 hasLocation W28914380601 @default.
- W2891438060 hasOpenAccess W2891438060 @default.
- W2891438060 hasPrimaryLocation W28914380601 @default.
- W2891438060 hasRelatedWork W1601492201 @default.
- W2891438060 hasRelatedWork W1967926704 @default.
- W2891438060 hasRelatedWork W1969590113 @default.
- W2891438060 hasRelatedWork W2015447694 @default.
- W2891438060 hasRelatedWork W2367122702 @default.
- W2891438060 hasRelatedWork W2369061952 @default.
- W2891438060 hasRelatedWork W2370645350 @default.
- W2891438060 hasRelatedWork W2383495548 @default.
- W2891438060 hasRelatedWork W4231036715 @default.
- W2891438060 hasRelatedWork W4382618573 @default.
- W2891438060 isParatext "false" @default.
- W2891438060 isRetracted "false" @default.
- W2891438060 magId "2891438060" @default.
- W2891438060 workType "article" @default.