FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3028321000> ?p ?o ?g. }

• W3028321000 abstract "Scene text recognition is a hot research topic in computer vision. Recently, many recognition methods based on the encoder-decoder framework have been proposed, and they can handle scene texts of perspective distortion and curve shape. Nevertheless, they still face lots of challenges like image blur, uneven illumination, and incomplete characters. We argue that most encoder-decoder methods are based on local visual features without explicit global semantic information. In this work, we propose a semantics enhanced encoder-decoder framework to robustly recognize low-quality scene texts. The semantic information is used both in the encoder module for supervision and in the decoder module for initializing. In particular, the state-of-the art ASTER method is integrated into the proposed framework as an exemplar. Extensive experiments demonstrate that the proposed framework is more robust for low-quality text images, and achieves state-of-the-art results on several benchmark datasets." @default.
• W3028321000 created "2020-05-29" @default.
• W3028321000 creator A5016175345 @default.
• W3028321000 creator A5016775929 @default.
• W3028321000 creator A5026666926 @default.
• W3028321000 creator A5077114895 @default.
• W3028321000 creator A5080811169 @default.
• W3028321000 date "2020-05-21" @default.
• W3028321000 modified "2023-09-25" @default.
• W3028321000 title "SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition" @default.
• W3028321000 cites W1521064364 @default.
• W3028321000 cites W1903029394 @default.
• W3028321000 cites W1922126009 @default.
• W3028321000 cites W1971822075 @default.
• W3028321000 cites W1978729128 @default.
• W3028321000 cites W1981283549 @default.
• W3028321000 cites W1998042868 @default.
• W3028321000 cites W2008806374 @default.
• W3028321000 cites W2061802763 @default.
• W3028321000 cites W2122585011 @default.
• W3028321000 cites W2128409098 @default.
• W3028321000 cites W2130942839 @default.
• W3028321000 cites W2144554289 @default.
• W3028321000 cites W2146835493 @default.
• W3028321000 cites W2157331557 @default.
• W3028321000 cites W2185167094 @default.
• W3028321000 cites W2194187530 @default.
• W3028321000 cites W2294053032 @default.
• W3028321000 cites W2341629100 @default.
• W3028321000 cites W2343052201 @default.
• W3028321000 cites W2493916176 @default.
• W3028321000 cites W2519818067 @default.
• W3028321000 cites W2520774189 @default.
• W3028321000 cites W2532759528 @default.
• W3028321000 cites W2548026590 @default.
• W3028321000 cites W2604186312 @default.
• W3028321000 cites W2605982830 @default.
• W3028321000 cites W2613718673 @default.
• W3028321000 cites W2740767790 @default.
• W3028321000 cites W2788069964 @default.
• W3028321000 cites W2788840914 @default.
• W3028321000 cites W2795619303 @default.
• W3028321000 cites W2809545542 @default.
• W3028321000 cites W2810648379 @default.
• W3028321000 cites W2810983211 @default.
• W3028321000 cites W2894730515 @default.
• W3028321000 cites W2895741527 @default.
• W3028321000 cites W2962773189 @default.
• W3028321000 cites W2962790387 @default.
• W3028321000 cites W2963233387 @default.
• W3028321000 cites W2963327605 @default.
• W3028321000 cites W2963351448 @default.
• W3028321000 cites W2963360699 @default.
• W3028321000 cites W2963517393 @default.
• W3028321000 cites W2963526661 @default.
• W3028321000 cites W2963585992 @default.
• W3028321000 cites W2963712589 @default.
• W3028321000 cites W2964308564 @default.
• W3028321000 cites W2965066169 @default.
• W3028321000 cites W2969549355 @default.
• W3028321000 cites W2970575838 @default.
• W3028321000 cites W2970971581 @default.
• W3028321000 cites W2979371747 @default.
• W3028321000 cites W3003861315 @default.
• W3028321000 cites W3106250896 @default.
• W3028321000 cites W603908379 @default.
• W3028321000 cites W6908809 @default.
• W3028321000 doi "https://doi.org/10.48550/arxiv.2005.10977" @default.
• W3028321000 hasPublicationYear "2020" @default.
• W3028321000 type Work @default.
• W3028321000 sameAs 3028321000 @default.
• W3028321000 citedByCount "0" @default.
• W3028321000 crossrefType "posted-content" @default.
• W3028321000 hasAuthorship W3028321000A5016175345 @default.
• W3028321000 hasAuthorship W3028321000A5016775929 @default.
• W3028321000 hasAuthorship W3028321000A5026666926 @default.
• W3028321000 hasAuthorship W3028321000A5077114895 @default.
• W3028321000 hasAuthorship W3028321000A5080811169 @default.
• W3028321000 hasBestOaLocation W30283210001 @default.
• W3028321000 hasConcept C111919701 @default.
• W3028321000 hasConcept C114466953 @default.
• W3028321000 hasConcept C118505674 @default.
• W3028321000 hasConcept C126780896 @default.
• W3028321000 hasConcept C12713177 @default.
• W3028321000 hasConcept C13280743 @default.
• W3028321000 hasConcept C154945302 @default.
• W3028321000 hasConcept C184337299 @default.
• W3028321000 hasConcept C185798385 @default.
• W3028321000 hasConcept C194257627 @default.
• W3028321000 hasConcept C199360897 @default.
• W3028321000 hasConcept C205649164 @default.
• W3028321000 hasConcept C2776257435 @default.
• W3028321000 hasConcept C31258907 @default.
• W3028321000 hasConcept C31972630 @default.
• W3028321000 hasConcept C41008148 @default.
• W3028321000 hasConceptScore W3028321000C111919701 @default.
• W3028321000 hasConceptScore W3028321000C114466953 @default.
• W3028321000 hasConceptScore W3028321000C118505674 @default.
• W3028321000 hasConceptScore W3028321000C126780896 @default.
• W3028321000 hasConceptScore W3028321000C12713177 @default.

• next