FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2776292203> ?p ?o ?g. }

• W2776292203 abstract "Scene Text Recognition is an extremely useful but challenging task and has drawn much attention in recent years. The best of previous model is CNN-LSTM model with attention mechanism, and it can recognize the whole text without character-level segmentation and recognition. Compared with LSTM, Recurrent Highway Networks (RHN), as a popular architecture because of its capability of training deep structure, can preform excellently in plenty of situations and has least parameters. Thus, we employ RHN as decoder and combine attention mechanism with it. Moreover, we integrate feature extraction, feature attention and sequence recognition into an end- to-end framework which can be jointly trained. Our proposed method is conducted on challenging public datasets, such as Street View Text and ICDAR 2003, and outperform the results of the best model in some datasets. Nevertheless, our model only contains 6.3 million parameters that is the minimal size of model for this problem." @default.
• W2776292203 created "2018-01-05" @default.
• W2776292203 creator A5033077540 @default.
• W2776292203 creator A5046308214 @default.
• W2776292203 creator A5072641204 @default.
• W2776292203 creator A5074514262 @default.
• W2776292203 creator A5076058977 @default.
• W2776292203 date "2017-11-01" @default.
• W2776292203 modified "2023-10-06" @default.
• W2776292203 title "Recurrent Highway Networks with Attention Mechanism for Scene Text Recognition" @default.
• W2776292203 cites W1557952530 @default.
• W2776292203 cites W1895191496 @default.
• W2776292203 cites W1922126009 @default.
• W2776292203 cites W1975453746 @default.
• W2776292203 cites W1981283549 @default.
• W2776292203 cites W1990550880 @default.
• W2776292203 cites W1998042868 @default.
• W2776292203 cites W2008806374 @default.
• W2776292203 cites W2022075901 @default.
• W2776292203 cites W2053317383 @default.
• W2776292203 cites W2064675550 @default.
• W2776292203 cites W2083442372 @default.
• W2776292203 cites W2097117768 @default.
• W2776292203 cites W2099247484 @default.
• W2776292203 cites W2122221966 @default.
• W2776292203 cites W2127141656 @default.
• W2776292203 cites W2143612262 @default.
• W2776292203 cites W2153182373 @default.
• W2776292203 cites W2160069326 @default.
• W2776292203 cites W2262249176 @default.
• W2776292203 cites W2294053032 @default.
• W2776292203 cites W2552853657 @default.
• W2776292203 cites W2950477116 @default.
• W2776292203 cites W2962707697 @default.
• W2776292203 cites W2963983719 @default.
• W2776292203 cites W2964300754 @default.
• W2776292203 cites W3099884890 @default.
• W2776292203 cites W70975097 @default.
• W2776292203 cites W753012316 @default.
• W2776292203 doi "https://doi.org/10.1109/dicta.2017.8227484" @default.
• W2776292203 hasPublicationYear "2017" @default.
• W2776292203 type Work @default.
• W2776292203 sameAs 2776292203 @default.
• W2776292203 citedByCount "2" @default.
• W2776292203 countsByYear W27762922032018 @default.
• W2776292203 countsByYear W27762922032020 @default.
• W2776292203 crossrefType "proceedings-article" @default.
• W2776292203 hasAuthorship W2776292203A5033077540 @default.
• W2776292203 hasAuthorship W2776292203A5046308214 @default.
• W2776292203 hasAuthorship W2776292203A5072641204 @default.
• W2776292203 hasAuthorship W2776292203A5074514262 @default.
• W2776292203 hasAuthorship W2776292203A5076058977 @default.
• W2776292203 hasConcept C111472728 @default.
• W2776292203 hasConcept C115961682 @default.
• W2776292203 hasConcept C119857082 @default.
• W2776292203 hasConcept C123657996 @default.
• W2776292203 hasConcept C138885662 @default.
• W2776292203 hasConcept C142362112 @default.
• W2776292203 hasConcept C153180895 @default.
• W2776292203 hasConcept C153349607 @default.
• W2776292203 hasConcept C154945302 @default.
• W2776292203 hasConcept C162324750 @default.
• W2776292203 hasConcept C187736073 @default.
• W2776292203 hasConcept C2776401178 @default.
• W2776292203 hasConcept C2778112365 @default.
• W2776292203 hasConcept C2780451532 @default.
• W2776292203 hasConcept C2983812711 @default.
• W2776292203 hasConcept C41008148 @default.
• W2776292203 hasConcept C41895202 @default.
• W2776292203 hasConcept C52622490 @default.
• W2776292203 hasConcept C54355233 @default.
• W2776292203 hasConcept C86803240 @default.
• W2776292203 hasConcept C89600930 @default.
• W2776292203 hasConcept C89611455 @default.
• W2776292203 hasConceptScore W2776292203C111472728 @default.
• W2776292203 hasConceptScore W2776292203C115961682 @default.
• W2776292203 hasConceptScore W2776292203C119857082 @default.
• W2776292203 hasConceptScore W2776292203C123657996 @default.
• W2776292203 hasConceptScore W2776292203C138885662 @default.
• W2776292203 hasConceptScore W2776292203C142362112 @default.
• W2776292203 hasConceptScore W2776292203C153180895 @default.
• W2776292203 hasConceptScore W2776292203C153349607 @default.
• W2776292203 hasConceptScore W2776292203C154945302 @default.
• W2776292203 hasConceptScore W2776292203C162324750 @default.
• W2776292203 hasConceptScore W2776292203C187736073 @default.
• W2776292203 hasConceptScore W2776292203C2776401178 @default.
• W2776292203 hasConceptScore W2776292203C2778112365 @default.
• W2776292203 hasConceptScore W2776292203C2780451532 @default.
• W2776292203 hasConceptScore W2776292203C2983812711 @default.
• W2776292203 hasConceptScore W2776292203C41008148 @default.
• W2776292203 hasConceptScore W2776292203C41895202 @default.
• W2776292203 hasConceptScore W2776292203C52622490 @default.
• W2776292203 hasConceptScore W2776292203C54355233 @default.
• W2776292203 hasConceptScore W2776292203C86803240 @default.
• W2776292203 hasConceptScore W2776292203C89600930 @default.
• W2776292203 hasConceptScore W2776292203C89611455 @default.
• W2776292203 hasLocation W27762922031 @default.
• W2776292203 hasOpenAccess W2776292203 @default.
• W2776292203 hasPrimaryLocation W27762922031 @default.
• W2776292203 hasRelatedWork W2329534601 @default.

• next