Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385542421> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4385542421 endingPage "3392" @default.
- W4385542421 startingPage "3392" @default.
- W4385542421 abstract "Dongba scripture sentence segmentation is an important and basic work in the digitization and machine translation of Dongba scripture. Dongba scripture sentence segmentation line detection (DS-SSLD) as a core technology of Dongba scripture sentence segmentation is a challenging task due to its own distinctiveness, such as high inherent noise interference and nonstandard sentence segmentation lines. Recently, projection-based methods have been adopted. However, these methods are difficult when dealing with the following two problems. The first is the noisy problem, where a large number of noise in the Dongba scripture image interference detection results. The second is the Dongba scripture inherent characteristics, where many vertical lines in Dongba hieroglyphs are easily confused with the vertical sentence segmentation lines. Therefore, this paper aims to propose a module based on the convolutional neural network (CNN) to improve the accuracy of DS-SSLD. To achieve this, we first construct a tagged dataset for training and testing DS-SSLD, including 2504 real images collected from Dongba scripture books and sentence segmentation targets. Then, we propose a multi-scale hybrid attention network (Multi-HAN) based on YOLOv5s, where a multiple hybrid attention unit (MHAU) is used to enhance the distinction between important features and redundant features, and the multi-scale cross-stage partial unit (Multi-CSPU) is used to realize multi-scale and richer feature representation. The experiment is carried out on the Dongba scripture sentence segmentation dataset we built. The experimental results show that the proposed method exhibits excellent detection performance and outperforms several state-of-the-art methods." @default.
- W4385542421 created "2023-08-04" @default.
- W4385542421 creator A5007142021 @default.
- W4385542421 creator A5036782157 @default.
- W4385542421 creator A5069980045 @default.
- W4385542421 date "2023-08-03" @default.
- W4385542421 modified "2023-09-29" @default.
- W4385542421 title "A Multi-Scale Hybrid Attention Network for Sentence Segmentation Line Detection in Dongba Scripture" @default.
- W4385542421 cites W2135209903 @default.
- W4385542421 cites W2140405352 @default.
- W4385542421 cites W2142085250 @default.
- W4385542421 cites W2159558889 @default.
- W4385542421 cites W2490270993 @default.
- W4385542421 cites W2565639579 @default.
- W4385542421 cites W2752782242 @default.
- W4385542421 cites W2807321692 @default.
- W4385542421 cites W2884585870 @default.
- W4385542421 cites W2886335102 @default.
- W4385542421 cites W2963068995 @default.
- W4385542421 cites W2964241181 @default.
- W4385542421 cites W2972395464 @default.
- W4385542421 cites W3003496674 @default.
- W4385542421 cites W3004127423 @default.
- W4385542421 cites W3016719260 @default.
- W4385542421 cites W3034552520 @default.
- W4385542421 cites W3042011474 @default.
- W4385542421 cites W3048265489 @default.
- W4385542421 cites W3106250896 @default.
- W4385542421 cites W3119205652 @default.
- W4385542421 cites W3213487195 @default.
- W4385542421 cites W4205933913 @default.
- W4385542421 cites W4206135140 @default.
- W4385542421 cites W4214666412 @default.
- W4385542421 cites W4309568943 @default.
- W4385542421 cites W4319065888 @default.
- W4385542421 cites W4382681035 @default.
- W4385542421 doi "https://doi.org/10.3390/math11153392" @default.
- W4385542421 hasPublicationYear "2023" @default.
- W4385542421 type Work @default.
- W4385542421 citedByCount "0" @default.
- W4385542421 crossrefType "journal-article" @default.
- W4385542421 hasAuthorship W4385542421A5007142021 @default.
- W4385542421 hasAuthorship W4385542421A5036782157 @default.
- W4385542421 hasAuthorship W4385542421A5069980045 @default.
- W4385542421 hasBestOaLocation W43855424211 @default.
- W4385542421 hasConcept C115961682 @default.
- W4385542421 hasConcept C138885662 @default.
- W4385542421 hasConcept C153180895 @default.
- W4385542421 hasConcept C154945302 @default.
- W4385542421 hasConcept C198352243 @default.
- W4385542421 hasConcept C205649164 @default.
- W4385542421 hasConcept C2524010 @default.
- W4385542421 hasConcept C2776401178 @default.
- W4385542421 hasConcept C2777530160 @default.
- W4385542421 hasConcept C2778755073 @default.
- W4385542421 hasConcept C28490314 @default.
- W4385542421 hasConcept C33923547 @default.
- W4385542421 hasConcept C41008148 @default.
- W4385542421 hasConcept C41895202 @default.
- W4385542421 hasConcept C58640448 @default.
- W4385542421 hasConcept C89600930 @default.
- W4385542421 hasConcept C99498987 @default.
- W4385542421 hasConceptScore W4385542421C115961682 @default.
- W4385542421 hasConceptScore W4385542421C138885662 @default.
- W4385542421 hasConceptScore W4385542421C153180895 @default.
- W4385542421 hasConceptScore W4385542421C154945302 @default.
- W4385542421 hasConceptScore W4385542421C198352243 @default.
- W4385542421 hasConceptScore W4385542421C205649164 @default.
- W4385542421 hasConceptScore W4385542421C2524010 @default.
- W4385542421 hasConceptScore W4385542421C2776401178 @default.
- W4385542421 hasConceptScore W4385542421C2777530160 @default.
- W4385542421 hasConceptScore W4385542421C2778755073 @default.
- W4385542421 hasConceptScore W4385542421C28490314 @default.
- W4385542421 hasConceptScore W4385542421C33923547 @default.
- W4385542421 hasConceptScore W4385542421C41008148 @default.
- W4385542421 hasConceptScore W4385542421C41895202 @default.
- W4385542421 hasConceptScore W4385542421C58640448 @default.
- W4385542421 hasConceptScore W4385542421C89600930 @default.
- W4385542421 hasConceptScore W4385542421C99498987 @default.
- W4385542421 hasIssue "15" @default.
- W4385542421 hasLocation W43855424211 @default.
- W4385542421 hasOpenAccess W4385542421 @default.
- W4385542421 hasPrimaryLocation W43855424211 @default.
- W4385542421 hasRelatedWork W2033914206 @default.
- W4385542421 hasRelatedWork W2035950535 @default.
- W4385542421 hasRelatedWork W2146076056 @default.
- W4385542421 hasRelatedWork W2351555819 @default.
- W4385542421 hasRelatedWork W2358941527 @default.
- W4385542421 hasRelatedWork W2382607599 @default.
- W4385542421 hasRelatedWork W2394327295 @default.
- W4385542421 hasRelatedWork W2532775738 @default.
- W4385542421 hasRelatedWork W2546942002 @default.
- W4385542421 hasRelatedWork W2970216048 @default.
- W4385542421 hasVolume "11" @default.
- W4385542421 isParatext "false" @default.
- W4385542421 isRetracted "false" @default.
- W4385542421 workType "article" @default.