Matches in SemOpenAlex for { <https://semopenalex.org/work/W4362468171> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4362468171 endingPage "4434" @default.
- W4362468171 startingPage "4434" @default.
- W4362468171 abstract "Problems such as complex image backgrounds, low image quality, diverse text forms, and similar or common character layouts in different script categories in natural scenes pose great challenges to scene script identification. This paper proposes a new Res2Net-based improved script identification method, namely FAS-Res2Net. In the feature extraction part, the feature pyramid network (FPN) module is introduced, which is beneficial to aggregate the geometric feature information extracted by the shallow network and the semantic feature information extracted by the deep network. Integrating the Adaptive Spatial Feature Fusion (ASFF) module is beneficial to obtain local feature information for optimal weight fusion. In addition, the global feature information of the image is extracted by introducing the swin transformer coding block, which makes the extracted feature information more abundant. In the classification part, the convolutional classifier is used to replace the traditional Linear classification, and the classification confidence of each category is output, which improves the identification efficiency. The improved algorithm achieved identification rates of 94.7% and 96.0% on public script identification datasets SIW-13 and CVSI-2015, respectively, which verified the superiority of the method." @default.
- W4362468171 created "2023-04-05" @default.
- W4362468171 creator A5041317342 @default.
- W4362468171 creator A5047735571 @default.
- W4362468171 creator A5048415051 @default.
- W4362468171 creator A5054655736 @default.
- W4362468171 creator A5066506917 @default.
- W4362468171 date "2023-03-31" @default.
- W4362468171 modified "2023-10-14" @default.
- W4362468171 title "FAS-Res2net: An Improved Res2net-Based Script Identification Method for Natural Scenes" @default.
- W4362468171 cites W2137456081 @default.
- W4362468171 cites W2196303045 @default.
- W4362468171 cites W2278889731 @default.
- W4362468171 cites W2283312651 @default.
- W4362468171 cites W2782396879 @default.
- W4362468171 cites W2783323081 @default.
- W4362468171 cites W2785557816 @default.
- W4362468171 cites W2928165649 @default.
- W4362468171 cites W2955793676 @default.
- W4362468171 cites W2963526661 @default.
- W4362468171 cites W2964057904 @default.
- W4362468171 cites W3003752723 @default.
- W4362468171 cites W3038540011 @default.
- W4362468171 cites W3080406710 @default.
- W4362468171 cites W3090645736 @default.
- W4362468171 cites W3099183222 @default.
- W4362468171 cites W3106887146 @default.
- W4362468171 cites W3114720220 @default.
- W4362468171 cites W3121092655 @default.
- W4362468171 cites W3127859904 @default.
- W4362468171 cites W3128636476 @default.
- W4362468171 cites W3138516171 @default.
- W4362468171 cites W3156147976 @default.
- W4362468171 cites W3156313549 @default.
- W4362468171 cites W3160412534 @default.
- W4362468171 cites W3172759799 @default.
- W4362468171 cites W3175706072 @default.
- W4362468171 cites W4214872252 @default.
- W4362468171 cites W4247050319 @default.
- W4362468171 cites W4284685252 @default.
- W4362468171 doi "https://doi.org/10.3390/app13074434" @default.
- W4362468171 hasPublicationYear "2023" @default.
- W4362468171 type Work @default.
- W4362468171 citedByCount "0" @default.
- W4362468171 crossrefType "journal-article" @default.
- W4362468171 hasAuthorship W4362468171A5041317342 @default.
- W4362468171 hasAuthorship W4362468171A5047735571 @default.
- W4362468171 hasAuthorship W4362468171A5048415051 @default.
- W4362468171 hasAuthorship W4362468171A5054655736 @default.
- W4362468171 hasAuthorship W4362468171A5066506917 @default.
- W4362468171 hasBestOaLocation W43624681711 @default.
- W4362468171 hasConcept C116834253 @default.
- W4362468171 hasConcept C138885662 @default.
- W4362468171 hasConcept C153180895 @default.
- W4362468171 hasConcept C154945302 @default.
- W4362468171 hasConcept C2776401178 @default.
- W4362468171 hasConcept C41008148 @default.
- W4362468171 hasConcept C41895202 @default.
- W4362468171 hasConcept C52622490 @default.
- W4362468171 hasConcept C59822182 @default.
- W4362468171 hasConcept C86803240 @default.
- W4362468171 hasConcept C95623464 @default.
- W4362468171 hasConceptScore W4362468171C116834253 @default.
- W4362468171 hasConceptScore W4362468171C138885662 @default.
- W4362468171 hasConceptScore W4362468171C153180895 @default.
- W4362468171 hasConceptScore W4362468171C154945302 @default.
- W4362468171 hasConceptScore W4362468171C2776401178 @default.
- W4362468171 hasConceptScore W4362468171C41008148 @default.
- W4362468171 hasConceptScore W4362468171C41895202 @default.
- W4362468171 hasConceptScore W4362468171C52622490 @default.
- W4362468171 hasConceptScore W4362468171C59822182 @default.
- W4362468171 hasConceptScore W4362468171C86803240 @default.
- W4362468171 hasConceptScore W4362468171C95623464 @default.
- W4362468171 hasIssue "7" @default.
- W4362468171 hasLocation W43624681711 @default.
- W4362468171 hasOpenAccess W4362468171 @default.
- W4362468171 hasPrimaryLocation W43624681711 @default.
- W4362468171 hasRelatedWork W1964120219 @default.
- W4362468171 hasRelatedWork W2000165426 @default.
- W4362468171 hasRelatedWork W2144059113 @default.
- W4362468171 hasRelatedWork W2146076056 @default.
- W4362468171 hasRelatedWork W2385132419 @default.
- W4362468171 hasRelatedWork W2546942002 @default.
- W4362468171 hasRelatedWork W2563096758 @default.
- W4362468171 hasRelatedWork W2772780115 @default.
- W4362468171 hasRelatedWork W2811390910 @default.
- W4362468171 hasRelatedWork W3003836766 @default.
- W4362468171 hasVolume "13" @default.
- W4362468171 isParatext "false" @default.
- W4362468171 isRetracted "false" @default.
- W4362468171 workType "article" @default.