{"id":"https://openalex.org/W4385872197","doi":"https://doi.org/10.3390/jimaging9080162","title":"Thangka Image Captioning Based on Semantic Concept Prompt and Multimodal Feature Optimization","display_name":"Thangka Image Captioning Based on Semantic Concept Prompt and Multimodal Feature Optimization","publication_year":2023,"publication_date":"2023-08-16","ids":{"openalex":"https://openalex.org/W4385872197","doi":"https://doi.org/10.3390/jimaging9080162","pmid":"https://pubmed.ncbi.nlm.nih.gov/37623694"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging9080162","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging9080162","pdf_url":"https://www.mdpi.com/2313-433X/9/8/162/pdf?version=1692178725","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2313-433X/9/8/162/pdf?version=1692178725","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025019727","display_name":"Wenjin Hu","orcid":"https://orcid.org/0000-0002-3120-5231"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenjin Hu","raw_affiliation_strings":["School of Mathematics and Computer Science, Northwest Minzu Univsersity, Lanzhou 730030, China"],"raw_orcid":"https://orcid.org/0000-0002-3120-5231","affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer Science, Northwest Minzu Univsersity, Lanzhou 730030, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101068097","display_name":"Lang Qiao","orcid":"https://orcid.org/0009-0001-9324-2556"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lang Qiao","raw_affiliation_strings":["Key Laboratory of China\u2019s Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou 730030, China","Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou 730030, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of China\u2019s Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou 730030, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou 730030, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074848650","display_name":"Wendong Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wendong Kang","raw_affiliation_strings":["Key Laboratory of China\u2019s Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou 730030, China","Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou 730030, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of China\u2019s Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou 730030, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou 730030, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114133147","display_name":"Xinyue Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyue Shi","raw_affiliation_strings":["Key Laboratory of China\u2019s Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou 730030, China","Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou 730030, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of China\u2019s Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou 730030, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou 730030, China","institution_ids":["https://openalex.org/I145897649"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5025019727"],"corresponding_institution_ids":["https://openalex.org/I145897649"],"apc_list":{"value":1800,"currency":"CHF","value_usd":2172},"apc_paid":{"value":1800,"currency":"CHF","value_usd":2172},"fwci":0.8543,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.71336734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"9","issue":"8","first_page":"162","last_page":"162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8820984959602356},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.84184330701828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6878237724304199},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6359413862228394},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45115339756011963},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4448683261871338},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4448024034500122},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4099324941635132},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32025614380836487},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07168543338775635}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8820984959602356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.84184330701828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6878237724304199},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6359413862228394},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45115339756011963},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4448683261871338},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4448024034500122},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4099324941635132},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32025614380836487},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07168543338775635},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/jimaging9080162","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging9080162","pdf_url":"https://www.mdpi.com/2313-433X/9/8/162/pdf?version=1692178725","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:37623694","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37623694","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of imaging","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10455603","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10455603","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10455603/pdf/jimaging-09-00162.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Imaging","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:62dce0eb1e034310b65017ae1418c425","is_oa":true,"landing_page_url":"https://doaj.org/article/62dce0eb1e034310b65017ae1418c425","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging, Vol 9, Iss 8, p 162 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/jimaging9080162","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging9080162","pdf_url":"https://www.mdpi.com/2313-433X/9/8/162/pdf?version=1692178725","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"No poverty","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/1"}],"awards":[{"id":"https://openalex.org/G181495721","display_name":null,"funder_award_id":"62061042","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G1863234590","display_name":null,"funder_award_id":"2018[98]","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5067136081","display_name":null,"funder_award_id":"31920220037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G630077093","display_name":null,"funder_award_id":"No. 2018","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7975028941","display_name":null,"funder_award_id":"31920220037","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8562013255","display_name":"\u5723\u50cf\u7c7b\u5510\u5361\u56fe\u50cf\u7684\u6587\u672c\u63cf\u8ff0\u751f\u6210\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62061042","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G96447229","display_name":null,"funder_award_id":"2018[98]","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330200","display_name":"National Ethnic Affairs Commission of the People's Republic of China","ror":"https://ror.org/01p9g6b97"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385872197.pdf","grobid_xml":"https://content.openalex.org/works/W4385872197.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1549091818","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2109586012","https://openalex.org/W2123301721","https://openalex.org/W2131179926","https://openalex.org/W2149557440","https://openalex.org/W2506483933","https://openalex.org/W2575842049","https://openalex.org/W2585123518","https://openalex.org/W2620998106","https://openalex.org/W2745461083","https://openalex.org/W2787017828","https://openalex.org/W2950626540","https://openalex.org/W2963486920","https://openalex.org/W2966715458","https://openalex.org/W2970231061","https://openalex.org/W2970476646","https://openalex.org/W2997591391","https://openalex.org/W3035284526","https://openalex.org/W3044438666","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3138516171","https://openalex.org/W3164670515","https://openalex.org/W3177174258","https://openalex.org/W4210268062","https://openalex.org/W4225702709","https://openalex.org/W4312922092","https://openalex.org/W6632624163","https://openalex.org/W6725318829","https://openalex.org/W6751751081","https://openalex.org/W6766818547"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Thangka":[0,27,66,92,110,140],"images":[1,93],"exhibit":[2],"a":[3,36],"high":[4],"level":[5],"of":[6,23,75,108,124,144],"diversity":[7],"and":[8,10,21,40,94,105,114,149,156],"richness,":[9],"the":[11,55,65,73,76,89,99,102,109,112,120,125,139,168,172],"existing":[12],"deep":[13],"learning-based":[14],"image":[15,103],"captioning":[16],"methods":[17,170],"generate":[18],"poor":[19],"accuracy":[20],"richness":[22,74],"Chinese":[24],"captions":[25],"for":[26],"images.":[28],"To":[29],"address":[30],"this":[31,33,160],"issue,":[32],"paper":[34],"proposes":[35],"Semantic":[37,47],"Concept":[38,48],"Prompt":[39,49],"Multimodal":[41,80],"Feature":[42,81],"Optimization":[43,82],"network":[44],"(SCAMF-Net).":[45],"The":[46,79,127],"(SCP)":[50],"module":[51,84,97],"is":[52,85],"introduced":[53],"in":[54,142],"text":[56,106],"encoding":[57],"stage":[58],"to":[59,87,116,167],"obtain":[60],"more":[61,117],"semantic":[62],"information":[63],"about":[64],"by":[67,151],"introducing":[68],"contextual":[69],"prompts,":[70],"thus":[71],"enhancing":[72],"description":[77],"content.":[78],"(MFO)":[83],"proposed":[86,133],"optimize":[88],"correlation":[90,100],"between":[91,101],"text.":[95],"This":[96],"enhances":[98],"features":[104,107,123],"through":[111],"Captioner":[113],"Filter":[115],"accurately":[118],"describe":[119],"visual":[121],"concept":[122],"Thangka.":[126],"experimental":[128],"results":[129],"demonstrate":[130],"that":[131],"our":[132],"method":[134,161],"outperforms":[135],"baseline":[136],"models":[137],"on":[138,171],"dataset":[141],"terms":[143],"BLEU-4,":[145],"METEOR,":[146],"ROUGE,":[147],"CIDEr,":[148],"SPICE":[150],"8.7%,":[152],"7.9%,":[153],"8.2%,":[154],"76.6%,":[155],"5.7%,":[157],"respectively.":[158],"Furthermore,":[159],"also":[162],"exhibits":[163],"superior":[164],"performance":[165],"compared":[166],"state-of-the-art":[169],"public":[173],"MSCOCO":[174],"dataset.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}