Matches in SemOpenAlex for { <https://semopenalex.org/work/W2762208110> ?p ?o ?g. }
- W2762208110 abstract "Recognizing text in the wild is a really challenging task because of complex backgrounds, various illuminations and diverse distortions, even with deep neural networks (convolutional neural networks and recurrent neural networks). In the end-to-end training procedure for scene text recognition, the outputs of deep neural networks at different iterations are always demonstrated with diversity and complementarity for the target object (text). Here, a simple but effective deep learning method, an adaptive ensemble of deep neural networks (AdaDNNs), is proposed to simply select and adaptively combine classifier components at different iterations from the whole learning system. Furthermore, the ensemble is formulated as a Bayesian framework for classifier weighting and combination. A variety of experiments on several typical acknowledged benchmarks, i.e., ICDAR Robust Reading Competition (Challenge 1, 2 and 4) datasets, verify the surprised improvement from the baseline DNNs, and the effectiveness of AdaDNNs compared with the recent state-of-the-art methods." @default.
- W2762208110 created "2017-10-20" @default.
- W2762208110 creator A5034317074 @default.
- W2762208110 creator A5039807259 @default.
- W2762208110 creator A5047968661 @default.
- W2762208110 creator A5060969271 @default.
- W2762208110 creator A5061153551 @default.
- W2762208110 creator A5070033770 @default.
- W2762208110 creator A5074514262 @default.
- W2762208110 date "2017-10-10" @default.
- W2762208110 modified "2023-09-27" @default.
- W2762208110 title "AdaDNNs: Adaptive Ensemble of Deep Neural Networks for Scene Text Recognition." @default.
- W2762208110 cites W114517082 @default.
- W2762208110 cites W1491389626 @default.
- W2762208110 cites W1521064364 @default.
- W2762208110 cites W1557952530 @default.
- W2762208110 cites W1895191496 @default.
- W2762208110 cites W1922126009 @default.
- W2762208110 cites W1932188282 @default.
- W2762208110 cites W1988790447 @default.
- W2762208110 cites W1995052126 @default.
- W2762208110 cites W2006653496 @default.
- W2762208110 cites W2049951199 @default.
- W2762208110 cites W2053317383 @default.
- W2762208110 cites W2107244081 @default.
- W2762208110 cites W2122221966 @default.
- W2762208110 cites W2127141656 @default.
- W2762208110 cites W2131447359 @default.
- W2762208110 cites W2135231474 @default.
- W2762208110 cites W2138900418 @default.
- W2762208110 cites W2146989110 @default.
- W2762208110 cites W2150953273 @default.
- W2762208110 cites W2158878654 @default.
- W2762208110 cites W2159374016 @default.
- W2762208110 cites W2163876554 @default.
- W2762208110 cites W2194187530 @default.
- W2762208110 cites W2194775991 @default.
- W2762208110 cites W2253806798 @default.
- W2762208110 cites W2340583188 @default.
- W2762208110 cites W2436219157 @default.
- W2762208110 cites W2912934387 @default.
- W2762208110 cites W2951696358 @default.
- W2762208110 cites W2963446085 @default.
- W2762208110 cites W2963446712 @default.
- W2762208110 cites W70975097 @default.
- W2762208110 hasPublicationYear "2017" @default.
- W2762208110 type Work @default.
- W2762208110 sameAs 2762208110 @default.
- W2762208110 citedByCount "3" @default.
- W2762208110 countsByYear W27622081102018 @default.
- W2762208110 countsByYear W27622081102020 @default.
- W2762208110 crossrefType "posted-content" @default.
- W2762208110 hasAuthorship W2762208110A5034317074 @default.
- W2762208110 hasAuthorship W2762208110A5039807259 @default.
- W2762208110 hasAuthorship W2762208110A5047968661 @default.
- W2762208110 hasAuthorship W2762208110A5060969271 @default.
- W2762208110 hasAuthorship W2762208110A5061153551 @default.
- W2762208110 hasAuthorship W2762208110A5070033770 @default.
- W2762208110 hasAuthorship W2762208110A5074514262 @default.
- W2762208110 hasConcept C107673813 @default.
- W2762208110 hasConcept C108583219 @default.
- W2762208110 hasConcept C119857082 @default.
- W2762208110 hasConcept C126838900 @default.
- W2762208110 hasConcept C153180895 @default.
- W2762208110 hasConcept C154945302 @default.
- W2762208110 hasConcept C183115368 @default.
- W2762208110 hasConcept C202269582 @default.
- W2762208110 hasConcept C2984842247 @default.
- W2762208110 hasConcept C41008148 @default.
- W2762208110 hasConcept C50644808 @default.
- W2762208110 hasConcept C54355233 @default.
- W2762208110 hasConcept C71924100 @default.
- W2762208110 hasConcept C81363708 @default.
- W2762208110 hasConcept C86803240 @default.
- W2762208110 hasConcept C95623464 @default.
- W2762208110 hasConceptScore W2762208110C107673813 @default.
- W2762208110 hasConceptScore W2762208110C108583219 @default.
- W2762208110 hasConceptScore W2762208110C119857082 @default.
- W2762208110 hasConceptScore W2762208110C126838900 @default.
- W2762208110 hasConceptScore W2762208110C153180895 @default.
- W2762208110 hasConceptScore W2762208110C154945302 @default.
- W2762208110 hasConceptScore W2762208110C183115368 @default.
- W2762208110 hasConceptScore W2762208110C202269582 @default.
- W2762208110 hasConceptScore W2762208110C2984842247 @default.
- W2762208110 hasConceptScore W2762208110C41008148 @default.
- W2762208110 hasConceptScore W2762208110C50644808 @default.
- W2762208110 hasConceptScore W2762208110C54355233 @default.
- W2762208110 hasConceptScore W2762208110C71924100 @default.
- W2762208110 hasConceptScore W2762208110C81363708 @default.
- W2762208110 hasConceptScore W2762208110C86803240 @default.
- W2762208110 hasConceptScore W2762208110C95623464 @default.
- W2762208110 hasLocation W27622081101 @default.
- W2762208110 hasOpenAccess W2762208110 @default.
- W2762208110 hasPrimaryLocation W27622081101 @default.
- W2762208110 hasRelatedWork W1423376249 @default.
- W2762208110 hasRelatedWork W2000469266 @default.
- W2762208110 hasRelatedWork W2185531897 @default.
- W2762208110 hasRelatedWork W2306479452 @default.
- W2762208110 hasRelatedWork W2531141905 @default.
- W2762208110 hasRelatedWork W2739693977 @default.