Matches in SemOpenAlex for { <https://semopenalex.org/work/W2887688727> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2887688727 abstract "Recently, hidden Markov models (HMMs) have achieved promising results for offline handwritten Chinese text recognition. However, due to the large vocabulary of Chinese characters with each modeled by a uniform and fixed number of hidden states, a high demand of memory and computation is required. In this study, to address this issue, we present parsimonious HMMs via the state tying which can fully utilize the similarities among different Chinese characters. Two-step algorithm with the data-driven question-set is adopted to generate the tied-state pool using the likelihood measure. The proposed parsimonious HMMs with both Gaussian mixture models (GMMs) and deep neural networks (DNNs) as the emission distributions not only lead to a compact model but also improve the recognition accuracy via the data sharing for the tied states and the confusion decreasing among state classes. Tested on ICDAR-2013 competition database, in the best configured case, the new parsimonious DNN-HMM can yield a relative character error rate (CER) reduction of 6.2%, 25% reduction of model size and 60% reduction of decoding time over the conventional DNN-HMM. In the compact setting case of average 1-state HMM, our parsimonious DNN-HMM significantly outperforms the conventional DNN-HMM with a relative CER reduction of 35.5%." @default.
- W2887688727 created "2018-08-22" @default.
- W2887688727 creator A5004072156 @default.
- W2887688727 creator A5062755510 @default.
- W2887688727 creator A5066595711 @default.
- W2887688727 date "2018-08-01" @default.
- W2887688727 modified "2023-10-16" @default.
- W2887688727 title "Parsimonious HMMs for Offline Handwritten Chinese Text Recognition" @default.
- W2887688727 cites W1582482241 @default.
- W2887688727 cites W1978964824 @default.
- W2887688727 cites W2005035880 @default.
- W2887688727 cites W2033404582 @default.
- W2887688727 cites W2046932483 @default.
- W2887688727 cites W2096466030 @default.
- W2887688727 cites W2112796928 @default.
- W2887688727 cites W2125838338 @default.
- W2887688727 cites W2127141656 @default.
- W2887688727 cites W2140090592 @default.
- W2887688727 cites W2149834450 @default.
- W2887688727 cites W2156338447 @default.
- W2887688727 cites W2158069733 @default.
- W2887688727 cites W2565262489 @default.
- W2887688727 cites W2609112450 @default.
- W2887688727 cites W2905318381 @default.
- W2887688727 cites W2919115771 @default.
- W2887688727 cites W2962779710 @default.
- W2887688727 doi "https://doi.org/10.1109/icfhr-2018.2018.00034" @default.
- W2887688727 hasPublicationYear "2018" @default.
- W2887688727 type Work @default.
- W2887688727 sameAs 2887688727 @default.
- W2887688727 citedByCount "5" @default.
- W2887688727 countsByYear W28876887272018 @default.
- W2887688727 countsByYear W28876887272019 @default.
- W2887688727 countsByYear W28876887272021 @default.
- W2887688727 countsByYear W28876887272023 @default.
- W2887688727 crossrefType "proceedings-article" @default.
- W2887688727 hasAuthorship W2887688727A5004072156 @default.
- W2887688727 hasAuthorship W2887688727A5062755510 @default.
- W2887688727 hasAuthorship W2887688727A5066595711 @default.
- W2887688727 hasBestOaLocation W28876887272 @default.
- W2887688727 hasConcept C111335779 @default.
- W2887688727 hasConcept C11413529 @default.
- W2887688727 hasConcept C153180895 @default.
- W2887688727 hasConcept C154945302 @default.
- W2887688727 hasConcept C23224414 @default.
- W2887688727 hasConcept C2524010 @default.
- W2887688727 hasConcept C28490314 @default.
- W2887688727 hasConcept C33923547 @default.
- W2887688727 hasConcept C40969351 @default.
- W2887688727 hasConcept C41008148 @default.
- W2887688727 hasConcept C57273362 @default.
- W2887688727 hasConcept C61224824 @default.
- W2887688727 hasConceptScore W2887688727C111335779 @default.
- W2887688727 hasConceptScore W2887688727C11413529 @default.
- W2887688727 hasConceptScore W2887688727C153180895 @default.
- W2887688727 hasConceptScore W2887688727C154945302 @default.
- W2887688727 hasConceptScore W2887688727C23224414 @default.
- W2887688727 hasConceptScore W2887688727C2524010 @default.
- W2887688727 hasConceptScore W2887688727C28490314 @default.
- W2887688727 hasConceptScore W2887688727C33923547 @default.
- W2887688727 hasConceptScore W2887688727C40969351 @default.
- W2887688727 hasConceptScore W2887688727C41008148 @default.
- W2887688727 hasConceptScore W2887688727C57273362 @default.
- W2887688727 hasConceptScore W2887688727C61224824 @default.
- W2887688727 hasLocation W28876887271 @default.
- W2887688727 hasLocation W28876887272 @default.
- W2887688727 hasOpenAccess W2887688727 @default.
- W2887688727 hasPrimaryLocation W28876887271 @default.
- W2887688727 hasRelatedWork W2125964738 @default.
- W2887688727 hasRelatedWork W2150890698 @default.
- W2887688727 hasRelatedWork W2160650576 @default.
- W2887688727 hasRelatedWork W2164868312 @default.
- W2887688727 hasRelatedWork W2401394187 @default.
- W2887688727 hasRelatedWork W2405257913 @default.
- W2887688727 hasRelatedWork W3133710586 @default.
- W2887688727 hasRelatedWork W4245698648 @default.
- W2887688727 hasRelatedWork W4285282705 @default.
- W2887688727 hasRelatedWork W4324119469 @default.
- W2887688727 isParatext "false" @default.
- W2887688727 isRetracted "false" @default.
- W2887688727 magId "2887688727" @default.
- W2887688727 workType "article" @default.