{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T01:26:49Z","timestamp":1774488409891,"version":"3.50.1"},"reference-count":80,"publisher":"Emerald","issue":"3","license":[{"start":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T00:00:00Z","timestamp":1644969600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["EL"],"published-print":{"date-parts":[[2022,5,13]]},"abstract":"\nPurpose<\/jats:title>\nDunhuang murals are rich in cultural and artistic value. The purpose of this paper is to construct a novel mobile visual search (MVS) framework for Dunhuang murals, enabling users to efficiently search for similar, relevant and diversified images.<\/jats:p>\n<\/jats:sec>\n\nDesign\/methodology\/approach<\/jats:title>\nThe convolutional neural network (CNN) model is fine-tuned in the data set of Dunhuang murals. Image features are extracted through the fine-tuned CNN model, and the similarities between different candidate images and the query image are calculated by the dot product. Then, the candidate images are sorted by similarity, and semantic labels are extracted from the most similar image. Ontology semantic distance (OSD) is proposed to match relevant images using semantic labels. Furthermore, the improved DivScore is introduced to diversify search results.<\/jats:p>\n<\/jats:sec>\n\nFindings<\/jats:title>\nThe results illustrate that the fine-tuned ResNet152 is the best choice to search for similar images at the visual feature level, and OSD is the effective method to search for the relevant images at the semantic level. After re-ranking based on DivScore, the diversification of search results is improved.<\/jats:p>\n<\/jats:sec>\n\nOriginality\/value<\/jats:title>\nThis study collects and builds the Dunhuang mural data set and proposes an effective MVS framework for Dunhuang murals to protect and inherit Dunhuang cultural heritage. Similar, relevant and diversified Dunhuang murals are searched to meet different demands.<\/jats:p>\n<\/jats:sec>","DOI":"10.1108\/el-09-2021-0173","type":"journal-article","created":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T13:15:45Z","timestamp":1644930945000},"page":"121-139","source":"Crossref","is-referenced-by-count":9,"title":["Constructing a mobile visual search framework for Dunhuang murals based on fine-tuned CNN and ontology semantic distance"],"prefix":"10.1108","volume":"40","author":[{"given":"Ziming","family":"Zeng","sequence":"first","affiliation":[]},{"given":"Shouqiang","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Jingjing","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Yueyan","family":"Shen","sequence":"additional","affiliation":[]}],"member":"140","published-online":{"date-parts":[[2022,2,16]]},"reference":[{"key":"key2022051209585514300_ref001","first-page":"214","article-title":"KAZE features","volume-title":"European Conference on Computer Vision","year":"2012"},{"key":"key2022051209585514300_ref002","article-title":"Large scale distributed neural network training through online distillation","year":"2018"},{"key":"key2022051209585514300_ref003","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.eswa.2018.05.015","article-title":"Reverse image search for scientific data within and beyond the visible spectrum","volume":"109","year":"2018","journal-title":"Expert Systems with Applications"},{"key":"key2022051209585514300_ref004","first-page":"404","article-title":"SURF: Speeded up robust features","volume":"3951","year":"2006","journal-title":"Computer Vision and Image Understanding"},{"key":"key2022051209585514300_ref005","first-page":"335","article-title":"The use of MMR, diversity-based reranking for reordering documents and producing summaries","volume-title":"Proceedings of the 21st Annual International ACM SIGIR Conference","year":"1998"},{"issue":"9","key":"key2022051209585514300_ref006","first-page":"6","article-title":"Semantic annotation of image resources in digital humanities","volume":"32","year":"2020","journal-title":"Agricultural Library and Information"},{"issue":"12","key":"key2022051209585514300_ref007","first-page":"243","article-title":"Dunhuang mural inpainting algorithm based on information entropy and structural characteristics","volume":"57","year":"2020","journal-title":"Laser and Optoelectronics Progress"},{"key":"key2022051209585514300_ref008","first-page":"200","article-title":"Knowledge distillation with feature maps for image classification","volume-title":"Asian Conference on Computer Vision","year":"2018"},{"key":"key2022051209585514300_ref009","first-page":"337","article-title":"Ontology-based dynamic semantic annotation for social image retrieval","volume-title":"21st IEEE International Conference on Mobile Data Management (MDM \u201820)","year":"2020"},{"key":"key2022051209585514300_ref010","first-page":"1251","article-title":"Xception: deep learning with depthwise separable convolutions","year":"2017"},{"key":"key2022051209585514300_ref011","volume-title":"Complete Collection of Dunhuang Frescoes in China","year":"2006"},{"key":"key2022051209585514300_ref012","first-page":"873","article-title":"Comparative study of convolution neural network\u2019s relu and leaky-relu activation functions","year":"2019"},{"key":"key2022051209585514300_ref013","first-page":"5","article-title":"For Dunhuang grottoes forever existence","volume":"3","year":"2004","journal-title":"Dunhuang Research"},{"key":"key2022051209585514300_ref014","doi-asserted-by":"crossref","first-page":"99","DOI":"10.5194\/isprs-annals-IV-2-W2-99-2017","article-title":"Line-drawing enhanced interactive mural restoration for Dunhuang mogao grottoes","volume":"IV-2\/W2","year":"2017","journal-title":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences"},{"key":"key2022051209585514300_ref015","first-page":"317","article-title":"Mobile visual search for digital heritage applications","year":"2017"},{"issue":"3","key":"key2022051209585514300_ref016","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1109\/MMUL.2011.48","article-title":"Mobile visual search: architectures, technologies, and the emerging MPEG standard","volume":"18","year":"2011","journal-title":"IEEE Multimedia"},{"issue":"4","key":"key2022051209585514300_ref017","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/S0306-4573(97)00007-1","article-title":"Modeling and retrieving images by content","volume":"33","year":"1997","journal-title":"ManagementInformation Processing"},{"key":"key2022051209585514300_ref018","first-page":"770","article-title":"Deep residual learning for image recognition","year":"2016"},{"issue":"7","key":"key2022051209585514300_ref019","first-page":"38","article-title":"Distilling the knowledge in a neural network","volume":"14","year":"2015","journal-title":"Computer Science"},{"key":"key2022051209585514300_ref020","unstructured":"Hu, T.Q. (1993), \u201cAn introduction to Dunhuang grotto art\u201d, Dunhuang Research, available at: http:\/\/en.cnki.com.cn\/Article_en\/CJFDTOTAL-DHYJ199303002.htm"},{"key":"key2022051209585514300_ref021","first-page":"93","article-title":"The costumes and culture in the tang dynasty of Dunhuang frescoes","volume":"1","year":"2008","journal-title":"Journal of Jinzhong University"},{"key":"key2022051209585514300_ref022","article-title":"Densenet: implementing efficient convnet descriptor pyramids","year":"2014"},{"key":"key2022051209585514300_ref023","article-title":"Retrieving diverse social images at MediaEval 2014: challenge, dataset and evaluation","year":"2014"},{"issue":"6","key":"key2022051209585514300_ref024","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1007\/s11390-005-0855-x","article-title":"Visual ontology construction for digitized art image retrieval","volume":"20","year":"2005","journal-title":"Journal of Computer Science and Technology"},{"key":"key2022051209585514300_ref025","article-title":"Deep face recognition model compression via knowledge transfer and distillation","year":"2019"},{"key":"key2022051209585514300_ref026","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","year":"2012"},{"key":"key2022051209585514300_ref027","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.neunet.2020.12.022","article-title":"Quantization friendly MobileNet (QF-MobileNet) architecture for vision based applications on embedded platforms","volume":"136","year":"2021","journal-title":"Neural Networks"},{"issue":"4","key":"key2022051209585514300_ref028","first-page":"139","article-title":"Construction of mobile visual search mechanism of cultural heritage digital library based on big data","volume":"41","year":"2018","journal-title":"Information Studies: Theory and Application"},{"issue":"9","key":"key2022051209585514300_ref029","first-page":"1","article-title":"Dating ancient paintings of mogao grottoes using deeply learnt visual codes","volume":"61","year":"2018","journal-title":"Science China Information Sciences"},{"issue":"1","key":"key2022051209585514300_ref030","article-title":"Dunhuang decorative pattern digital intelligent enhancement algorithm","volume":"435","year":"2018","journal-title":"IOP Conference Series: Materials Science and Engineering"},{"issue":"24","key":"key2022051209585514300_ref031","doi-asserted-by":"crossref","first-page":"32107","DOI":"10.1007\/s11042-018-6210-3","article-title":"Indexing of the CNN features for the large scale image search","volume":"77","year":"2018","journal-title":"Multimedia Tools and Applications"},{"issue":"3","key":"key2022051209585514300_ref032","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1108\/EL-09-2018-0187","article-title":"Towards a semantics representation framework for narrative images","volume":"37","year":"2019","journal-title":"The Electronic Library"},{"issue":"2","key":"key2022051209585514300_ref033","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant key points","volume":"60","year":"2004","journal-title":"International Journal of Computer Vision"},{"key":"key2022051209585514300_ref034","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.ins.2019.06.020","article-title":"Result diversification in image retrieval based on semantic distance","volume":"502","year":"2019","journal-title":"Information Sciences"},{"issue":"1","key":"key2022051209585514300_ref035","first-page":"3560","article-title":"Face model compression by distilling knowledge from neurons","volume":"30","year":"2016","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"key2022051209585514300_ref036","first-page":"288","article-title":"Ontology based image retrieval","year":"2012"},{"issue":"6","key":"key2022051209585514300_ref037","doi-asserted-by":"crossref","first-page":"1191","DOI":"10.1108\/EL-06-2016-0127","article-title":"Semantic text-based image retrieval with multi-modality ontology and DBpedia","volume":"35","year":"2017","journal-title":"The Electronic Library"},{"key":"key2022051209585514300_ref038","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1145\/2103354.2103373","article-title":"Crowdsourcing in the cultural heritage domain: opportunities and challenges","volume-title":"Proceedings of the 5th International Conference on Communities and Technologies","year":"2011"},{"key":"key2022051209585514300_ref039","article-title":"Stacked auto-encoder based tagging with deep features for content-based medical image retrieval","volume":"161","year":"2020","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"key2022051209585514300_ref040","doi-asserted-by":"crossref","first-page":"84","DOI":"10.11591\/ijai.v10.i1.pp84-92","article-title":"Effect of data-augmentation on fine-tuned CNN model performance","volume":"10","year":"2021","journal-title":"IAES International Journal of Artificial Intelligence (IJ-AI)"},{"key":"key2022051209585514300_ref041","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.neucom.2017.05.025","article-title":"Medical image retrieval using deep convolutional neural network","volume":"266","year":"2017","journal-title":"Neurocomputing"},{"key":"key2022051209585514300_ref042","first-page":"29","article-title":"Digital humanities mobile visual search methods based on deep hashing","volume":"6","year":"2018","journal-title":"Information and Documentation Services"},{"issue":"7","key":"key2022051209585514300_ref043","first-page":"1655","article-title":"Fine-tuning CNN image retrieval with no human annotation","volume":"41","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"key2022051209585514300_ref044","first-page":"55","article-title":"Ontology-based information retrieval for historical documents","volume-title":"Third International Conference on Information Retrieval and Knowledge Management (CAMP \u201816)","year":"2016"},{"issue":"4","key":"key2022051209585514300_ref045","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1111\/cura.12046","article-title":"From tagging to theorizing: deepening engagement with cultural heritage through crowdsourcing","volume":"56","year":"2013","journal-title":"Curator: The Museum Journal"},{"issue":"6","key":"key2022051209585514300_ref046","first-page":"60","article-title":"Dunhuang: caves of the singing sands: Buddhist art from the silk road","volume":"50","year":"1997","journal-title":"Archaeology"},{"key":"key2022051209585514300_ref047","first-page":"2564","article-title":"ORB: an efficient alternative to SIFT or SURF","year":"2011"},{"key":"key2022051209585514300_ref048","first-page":"4510","article-title":"Mobilenetv2: inverted residuals and linear bottlenecks","year":"2018"},{"key":"key2022051209585514300_ref049","first-page":"87","article-title":"Explicit search result diversification through Sub-queries","volume-title":"European Conference on Information Retrieval","year":"2010"},{"key":"key2022051209585514300_ref050","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1016\/j.procs.2013.09.105","article-title":"Ontology based image retrieval framework using qualitative semantic image descriptions","volume":"22","year":"2013","journal-title":"Procedia Computer Science"},{"key":"key2022051209585514300_ref051","first-page":"1246","article-title":"Towards good practices for image retrieval based on CNN features","year":"2017"},{"key":"key2022051209585514300_ref052","article-title":"Digital object restoration using generalized regression neural network deep learning \u2013 taking Dunhuang mural restoration as an example","volume":"1","year":"2020","journal-title":"The International Journal of Electrical Engineering and Education"},{"key":"key2022051209585514300_ref053","article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014"},{"issue":"3","key":"key2022051209585514300_ref054","first-page":"319","article-title":"A new model of content image retrieval based on the ontology theory description","volume":"41","year":"2012","journal-title":"Information and Control"},{"key":"key2022051209585514300_ref055","unstructured":"Sun, H.G. (2013), \u201cMobile visual search\u201d, Master of Engineering research thesis, School of Electrical, Computer and Telecommunications Engineering, University of Wollongong."},{"issue":"1","key":"key2022051209585514300_ref056","first-page":"1","article-title":"What\u2019s wrong with the murals at the mogao grottoes: a near-infrared hyperspectral imaging method","volume":"5","year":"2015","journal-title":"Scientific Reports"},{"key":"key2022051209585514300_ref057","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","year":"2016"},{"key":"key2022051209585514300_ref058","first-page":"1","article-title":"Going deeper with convolutions","year":"2015"},{"key":"key2022051209585514300_ref059","first-page":"6105","article-title":"Efficientnet: rethinking model scaling for convolutional neural networks","year":"2019"},{"key":"key2022051209585514300_ref060","first-page":"204","article-title":"SemOIR: an ontology-based semantic information retrieval system","year":"2020","journal-title":"IEEE 20th International Conference on Software Quality, Reliability and Security Companion (QRS-C \u201820)"},{"key":"key2022051209585514300_ref061","first-page":"257","article-title":"Mobile cultural heritage guide: location-aware semantic search","year":"2010"},{"key":"key2022051209585514300_ref062","article-title":"Deep learning for content-based image retrieval: a comprehensive study","volume-title":"Proceedings of the 22nd ACM International Conference on Multimedia","year":"2014"},{"key":"key2022051209585514300_ref063","first-page":"57","article-title":"Moral education from the Dunhuang murals","volume":"1","year":"2019","journal-title":"The Dunhuang Grottoes and Global Education"},{"issue":"7","key":"key2022051209585514300_ref064","first-page":"604","article-title":"Representing and linking Dunhuang cultural heritage information resources using knowledge graph","volume":"47","year":"2021","journal-title":"Knowledge Organization"},{"issue":"19","key":"key2022051209585514300_ref065","first-page":"122","article-title":"Empirical research on semantic description model for Dunhuang fresco images","volume":"59","year":"2015","journal-title":"Library and Information Service"},{"issue":"3","key":"key2022051209585514300_ref066","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3280790","article-title":"Inpainting of Dunhuang murals by sparsely modeling the texture similarity and structure continuity","volume":"12","year":"2019","journal-title":"Journal on Computing and Cultural Heritage"},{"issue":"1","key":"key2022051209585514300_ref067","first-page":"50","article-title":"Semantic description framework research on Dunhuang fresco digital images","volume":"40","year":"2014","journal-title":"Journal of Library Science in China"},{"issue":"2","key":"key2022051209585514300_ref068","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1108\/JD-03-2017-0033","article-title":"Understanding subjects contained in Dunhuang mural images for deep semantic annotation","volume":"74","year":"2018","journal-title":"Journal of Documentation"},{"issue":"2","key":"key2022051209585514300_ref069","first-page":"22","article-title":"Topic extraction of intangible cultural heritage image resources based on associated labels","volume":"60","year":"2016","journal-title":"Library and Information Service"},{"issue":"5","key":"key2022051209585514300_ref070","first-page":"70","article-title":"Narrative image annotation ontology for semantic web","volume":"43","year":"2017","journal-title":"Journal of Library Science in China"},{"key":"key2022051209585514300_ref071","article-title":"HAGERec: Hierarchical attention graph convolutional network incorporating knowledge graph for explainable recommendation","volume":"204","year":"2020","journal-title":"Knowledge-Based Systems"},{"issue":"1","key":"key2022051209585514300_ref072","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1007\/s12204-014-1473-y","article-title":"Aesthetic visual style assessment on Dunhuang murals","volume":"19","year":"2014","journal-title":"Journal of Shanghai Jiaotong University (Science)"},{"issue":"2","key":"key2022051209585514300_ref073","first-page":"216","article-title":"Massive medical images retrieval system based on hadoop","volume":"9","year":"2014","journal-title":"Journal of Multimedia"},{"key":"key2022051209585514300_ref074","first-page":"120","article-title":"The design and implementation of the framework for the database of \u2018digital Dunhuang","volume":"2","year":"2020","journal-title":"Dunhuang Research"},{"issue":"2","key":"key2022051209585514300_ref075","first-page":"104","article-title":"Research on mobile visual search model for Dunhuang murals","volume":"42","year":"2021","journal-title":"Information and Documentation Services"},{"key":"key2022051209585514300_ref076","first-page":"431","article-title":"Aesthetic contemplation of the tang dynasty Dunhuang frescoes elements on contemporary costume design","year":"2020"},{"issue":"3","key":"key2022051209585514300_ref077","first-page":"114","article-title":"An overview of mobile visual search research abroad","volume":"40","year":"2014","journal-title":"Journal of Library Science in China"},{"key":"key2022051209585514300_ref078","first-page":"834","article-title":"Part-based R-CNNs for fine-grained category detection","volume-title":"European Conference on Computer Vision","year":"2014"},{"key":"key2022051209585514300_ref079","first-page":"232","article-title":"Study of agricultural drawings of Dunhuang frescoes in the tang and five dynasties","volume":"3","year":"2019","journal-title":"Agricultural Archaeology"},{"issue":"6","key":"key2022051209585514300_ref080","first-page":"13","article-title":"A probe into digital humanities visual resources semantic knowledge hierarchical aggregation service","volume":"39","year":"2018","journal-title":"Information and Documentation Services"}],"container-title":["The Electronic Library"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/EL-09-2021-0173\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/EL-09-2021-0173\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T01:08:04Z","timestamp":1753405684000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/el\/article\/40\/3\/121-139\/78241"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,16]]},"references-count":80,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2022,2,16]]},"published-print":{"date-parts":[[2022,5,13]]}},"alternative-id":["10.1108\/EL-09-2021-0173"],"URL":"https:\/\/doi.org\/10.1108\/el-09-2021-0173","relation":{},"ISSN":["0264-0473","0264-0473"],"issn-type":[{"value":"0264-0473","type":"print"},{"value":"0264-0473","type":"print"}],"subject":[],"published":{"date-parts":[[2022,2,16]]}}}