Matches in SemOpenAlex for { <https://semopenalex.org/work/W2769851275> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2769851275 abstract "In this paper, we propose a refined scene text detector with a textit{novel} Feature Enhancement Network (FEN) for Region Proposal and Text Detection Refinement. Retrospectively, both region proposal with textit{only} $3times 3$ sliding-window feature and text detection refinement with textit{single scale} high level feature are insufficient, especially for smaller scene text. Therefore, we design a new FEN network with textit{task-specific}, textit{low} and textit{high} level semantic features fusion to improve the performance of text detection. Besides, since textit{unitary} position-sensitive RoI pooling in general object detection is unreasonable for variable text regions, an textit{adaptively weighted} position-sensitive RoI pooling layer is devised for further enhancing the detecting accuracy. To tackle the textit{sample-imbalance} problem during the refinement stage, we also propose an effective textit{positives mining} strategy for efficiently training our network. Experiments on ICDAR 2011 and 2013 robust text detection benchmarks demonstrate that our method can achieve state-of-the-art results, outperforming all reported methods in terms of F-measure." @default.
- W2769851275 created "2017-12-04" @default.
- W2769851275 creator A5045160787 @default.
- W2769851275 creator A5047855118 @default.
- W2769851275 creator A5071461852 @default.
- W2769851275 creator A5080674767 @default.
- W2769851275 date "2017-11-12" @default.
- W2769851275 modified "2023-09-23" @default.
- W2769851275 title "Feature Enhancement Network: A Refined Scene Text Detector" @default.
- W2769851275 cites W1026856040 @default.
- W2769851275 cites W117491841 @default.
- W2769851275 cites W1539000009 @default.
- W2769851275 cites W1903029394 @default.
- W2769851275 cites W1922126009 @default.
- W2769851275 cites W1932624639 @default.
- W2769851275 cites W2020964295 @default.
- W2769851275 cites W2056518953 @default.
- W2769851275 cites W2061802763 @default.
- W2769851275 cites W2069472161 @default.
- W2769851275 cites W2117539524 @default.
- W2769851275 cites W2122221966 @default.
- W2769851275 cites W2128854450 @default.
- W2769851275 cites W2131447359 @default.
- W2769851275 cites W2337897552 @default.
- W2769851275 cites W2395360388 @default.
- W2769851275 cites W2407521645 @default.
- W2769851275 cites W2468724597 @default.
- W2769851275 cites W2519818067 @default.
- W2769851275 cites W2535388113 @default.
- W2769851275 cites W2750933790 @default.
- W2769851275 cites W2949650786 @default.
- W2769851275 cites W2951285986 @default.
- W2769851275 cites W2952302849 @default.
- W2769851275 cites W2952365771 @default.
- W2769851275 cites W2953106684 @default.
- W2769851275 cites W2962773189 @default.
- W2769851275 doi "https://doi.org/10.48550/arxiv.1711.04249" @default.
- W2769851275 hasPublicationYear "2017" @default.
- W2769851275 type Work @default.
- W2769851275 sameAs 2769851275 @default.
- W2769851275 citedByCount "2" @default.
- W2769851275 countsByYear W27698512752020 @default.
- W2769851275 crossrefType "posted-content" @default.
- W2769851275 hasAuthorship W2769851275A5045160787 @default.
- W2769851275 hasAuthorship W2769851275A5047855118 @default.
- W2769851275 hasAuthorship W2769851275A5071461852 @default.
- W2769851275 hasAuthorship W2769851275A5080674767 @default.
- W2769851275 hasBestOaLocation W27698512751 @default.
- W2769851275 hasConcept C10138342 @default.
- W2769851275 hasConcept C11413529 @default.
- W2769851275 hasConcept C124101348 @default.
- W2769851275 hasConcept C138885662 @default.
- W2769851275 hasConcept C153180895 @default.
- W2769851275 hasConcept C154945302 @default.
- W2769851275 hasConcept C162324750 @default.
- W2769851275 hasConcept C198082294 @default.
- W2769851275 hasConcept C2776401178 @default.
- W2769851275 hasConcept C2780009758 @default.
- W2769851275 hasConcept C41008148 @default.
- W2769851275 hasConcept C41895202 @default.
- W2769851275 hasConcept C64869954 @default.
- W2769851275 hasConcept C70437156 @default.
- W2769851275 hasConcept C76155785 @default.
- W2769851275 hasConcept C94915269 @default.
- W2769851275 hasConceptScore W2769851275C10138342 @default.
- W2769851275 hasConceptScore W2769851275C11413529 @default.
- W2769851275 hasConceptScore W2769851275C124101348 @default.
- W2769851275 hasConceptScore W2769851275C138885662 @default.
- W2769851275 hasConceptScore W2769851275C153180895 @default.
- W2769851275 hasConceptScore W2769851275C154945302 @default.
- W2769851275 hasConceptScore W2769851275C162324750 @default.
- W2769851275 hasConceptScore W2769851275C198082294 @default.
- W2769851275 hasConceptScore W2769851275C2776401178 @default.
- W2769851275 hasConceptScore W2769851275C2780009758 @default.
- W2769851275 hasConceptScore W2769851275C41008148 @default.
- W2769851275 hasConceptScore W2769851275C41895202 @default.
- W2769851275 hasConceptScore W2769851275C64869954 @default.
- W2769851275 hasConceptScore W2769851275C70437156 @default.
- W2769851275 hasConceptScore W2769851275C76155785 @default.
- W2769851275 hasConceptScore W2769851275C94915269 @default.
- W2769851275 hasLocation W27698512751 @default.
- W2769851275 hasOpenAccess W2769851275 @default.
- W2769851275 hasPrimaryLocation W27698512751 @default.
- W2769851275 hasRelatedWork W2015538044 @default.
- W2769851275 hasRelatedWork W2039076421 @default.
- W2769851275 hasRelatedWork W2043075591 @default.
- W2769851275 hasRelatedWork W2375904069 @default.
- W2769851275 hasRelatedWork W2901298109 @default.
- W2769851275 hasRelatedWork W2944724518 @default.
- W2769851275 hasRelatedWork W2951391129 @default.
- W2769851275 hasRelatedWork W2970216048 @default.
- W2769851275 hasRelatedWork W3202244193 @default.
- W2769851275 hasRelatedWork W4281640556 @default.
- W2769851275 isParatext "false" @default.
- W2769851275 isRetracted "false" @default.
- W2769851275 magId "2769851275" @default.
- W2769851275 workType "article" @default.