Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892774295> ?p ?o ?g. }
- W2892774295 abstract "In this work, we propose a novel hybrid method for scene text detection namely Correlation Propagation Network (CPN). It is an end-to-end trainable framework engined by advanced Convolutional Neural Networks. Our CPN predicts text objects according to both top-down observations and the bottom-up cues. Multiple candidate boxes are assembled by a spatial communication mechanism call Correlation Propagation (CP). The extracted spatial features by CNN are regarded as node features in a latticed graph and Correlation Propagation algorithm runs distributively on each node to update the hypothesis of corresponding object centers. The CP process can flexibly handle scale-varying and rotated text objects without using predefined bounding box templates. Benefit from its distributive nature, CPN is computationally efficient and enjoys a high level of parallelism. Moreover, we introduce deformable convolution to the backbone network to enhance the adaptability to long texts. The evaluation on public benchmarks shows that the proposed method achieves state-of-art performance, and it significantly outperforms the existing methods for handling multi-scale and multi-oriented text objects with much lower computation cost." @default.
- W2892774295 created "2018-10-05" @default.
- W2892774295 creator A5006294869 @default.
- W2892774295 creator A5013941213 @default.
- W2892774295 creator A5019708391 @default.
- W2892774295 creator A5029912845 @default.
- W2892774295 creator A5042271198 @default.
- W2892774295 creator A5042682339 @default.
- W2892774295 date "2018-09-30" @default.
- W2892774295 modified "2023-09-28" @default.
- W2892774295 title "Correlation Propagation Networks for Scene Text Detection." @default.
- W2892774295 cites W1026856040 @default.
- W2892774295 cites W117491841 @default.
- W2892774295 cites W1521064364 @default.
- W2892774295 cites W1607307044 @default.
- W2892774295 cites W1686810756 @default.
- W2892774295 cites W1922126009 @default.
- W2892774295 cites W1935817682 @default.
- W2892774295 cites W1972065312 @default.
- W2892774295 cites W2056518953 @default.
- W2892774295 cites W2061802763 @default.
- W2892774295 cites W2069472161 @default.
- W2892774295 cites W2112796928 @default.
- W2892774295 cites W2122221966 @default.
- W2892774295 cites W2128854450 @default.
- W2892774295 cites W2194775991 @default.
- W2892774295 cites W2271840356 @default.
- W2892774295 cites W2464918637 @default.
- W2892774295 cites W2504108613 @default.
- W2892774295 cites W2519818067 @default.
- W2892774295 cites W2565639579 @default.
- W2892774295 cites W2749425057 @default.
- W2892774295 cites W2755893652 @default.
- W2892774295 cites W2798591388 @default.
- W2892774295 cites W2950143680 @default.
- W2892774295 cites W2950477723 @default.
- W2892774295 cites W2951004565 @default.
- W2892774295 cites W2951285986 @default.
- W2892774295 cites W2951548327 @default.
- W2892774295 cites W2952302849 @default.
- W2892774295 cites W2952365771 @default.
- W2892774295 cites W2952662639 @default.
- W2892774295 cites W2953106684 @default.
- W2892774295 cites W2962773189 @default.
- W2892774295 cites W2963840241 @default.
- W2892774295 cites W654550266 @default.
- W2892774295 hasPublicationYear "2018" @default.
- W2892774295 type Work @default.
- W2892774295 sameAs 2892774295 @default.
- W2892774295 citedByCount "0" @default.
- W2892774295 crossrefType "posted-content" @default.
- W2892774295 hasAuthorship W2892774295A5006294869 @default.
- W2892774295 hasAuthorship W2892774295A5013941213 @default.
- W2892774295 hasAuthorship W2892774295A5019708391 @default.
- W2892774295 hasAuthorship W2892774295A5029912845 @default.
- W2892774295 hasAuthorship W2892774295A5042271198 @default.
- W2892774295 hasAuthorship W2892774295A5042682339 @default.
- W2892774295 hasConcept C111919701 @default.
- W2892774295 hasConcept C11413529 @default.
- W2892774295 hasConcept C115961682 @default.
- W2892774295 hasConcept C117220453 @default.
- W2892774295 hasConcept C121332964 @default.
- W2892774295 hasConcept C127413603 @default.
- W2892774295 hasConcept C132525143 @default.
- W2892774295 hasConcept C147037132 @default.
- W2892774295 hasConcept C150060386 @default.
- W2892774295 hasConcept C153180895 @default.
- W2892774295 hasConcept C154945302 @default.
- W2892774295 hasConcept C177606310 @default.
- W2892774295 hasConcept C18903297 @default.
- W2892774295 hasConcept C2524010 @default.
- W2892774295 hasConcept C2778755073 @default.
- W2892774295 hasConcept C33923547 @default.
- W2892774295 hasConcept C41008148 @default.
- W2892774295 hasConcept C45347329 @default.
- W2892774295 hasConcept C45374587 @default.
- W2892774295 hasConcept C48044578 @default.
- W2892774295 hasConcept C50644808 @default.
- W2892774295 hasConcept C62520636 @default.
- W2892774295 hasConcept C62611344 @default.
- W2892774295 hasConcept C63584917 @default.
- W2892774295 hasConcept C66938386 @default.
- W2892774295 hasConcept C76155785 @default.
- W2892774295 hasConcept C77088390 @default.
- W2892774295 hasConcept C80444323 @default.
- W2892774295 hasConcept C81363708 @default.
- W2892774295 hasConcept C86803240 @default.
- W2892774295 hasConcept C98045186 @default.
- W2892774295 hasConceptScore W2892774295C111919701 @default.
- W2892774295 hasConceptScore W2892774295C11413529 @default.
- W2892774295 hasConceptScore W2892774295C115961682 @default.
- W2892774295 hasConceptScore W2892774295C117220453 @default.
- W2892774295 hasConceptScore W2892774295C121332964 @default.
- W2892774295 hasConceptScore W2892774295C127413603 @default.
- W2892774295 hasConceptScore W2892774295C132525143 @default.
- W2892774295 hasConceptScore W2892774295C147037132 @default.
- W2892774295 hasConceptScore W2892774295C150060386 @default.
- W2892774295 hasConceptScore W2892774295C153180895 @default.
- W2892774295 hasConceptScore W2892774295C154945302 @default.
- W2892774295 hasConceptScore W2892774295C177606310 @default.