{"id":"https://openalex.org/W4406158020","doi":"https://doi.org/10.1109/access.2025.3526954","title":"Combining Region-Guided Attention and Attribute Prediction for Thangka Image Captioning Method","display_name":"Combining Region-Guided Attention and Attribute Prediction for Thangka Image Captioning Method","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406158020","doi":"https://doi.org/10.1109/access.2025.3526954"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3526954","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3526954","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3526954","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012162136","display_name":"Fujun Zhang","orcid":"https://orcid.org/0009-0004-9593-9930"},"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":"Fujun Zhang","raw_affiliation_strings":["Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Chinese National Information Technology Research Institute, Northwest Minzu University, Lanzhou, Gansu, China","Chinese National Information Technology Research Institute, Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Northwest Minzu University, Lanzhou, Gansu, China"],"raw_orcid":"https://orcid.org/0009-0004-9593-9930","affiliations":[{"raw_affiliation_string":"Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Chinese National Information Technology Research Institute, Northwest Minzu University, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Chinese National Information Technology Research Institute, Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Northwest Minzu University, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023034459","display_name":"Wendong Kang","orcid":"https://orcid.org/0000-0002-1983-1555"},"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 Linguistic and Cultural Computing of Ministry of Education, Chinese National Information Technology Research Institute, Northwest Minzu University, Lanzhou, Gansu, China","Chinese National Information Technology Research Institute, Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Northwest Minzu University, Lanzhou, Gansu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Chinese National Information Technology Research Institute, Northwest Minzu University, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Chinese National Information Technology Research Institute, Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Northwest Minzu University, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"last","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":false,"raw_author_name":"Wenjin Hu","raw_affiliation_strings":["Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Chinese National Information Technology Research Institute, Northwest Minzu University, Lanzhou, Gansu, China","Chinese National Information Technology Research Institute, Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Northwest Minzu University, Lanzhou, Gansu, China","School of Mathematics and Computer Science, Northwest Minzu University, Lanzhou, Gansu, China"],"raw_orcid":"https://orcid.org/0000-0002-3120-5231","affiliations":[{"raw_affiliation_string":"Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Chinese National Information Technology Research Institute, Northwest Minzu University, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Chinese National Information Technology Research Institute, Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Northwest Minzu University, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"School of Mathematics and Computer Science, Northwest Minzu University, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I145897649"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145897649"],"apc_list":{"value":2075,"currency":"USD","value_usd":2075},"apc_paid":{"value":2075,"currency":"USD","value_usd":2075},"fwci":0.923,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69725605,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"13","issue":null,"first_page":"13440","last_page":"13453"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980000257492065,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9898999929428101,"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":0.9531185626983643},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7629008293151855},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5924844741821289},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5462708473205566},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4082334637641907},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3770056366920471}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9531185626983643},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7629008293151855},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5924844741821289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5462708473205566},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4082334637641907},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3770056366920471}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3526954","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3526954","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:49a76f2ced8f4210a965f9b34367e04e","is_oa":true,"landing_page_url":"https://doaj.org/article/49a76f2ced8f4210a965f9b34367e04e","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":"IEEE Access, Vol 13, Pp 13440-13453 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3526954","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3526954","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6872681969","display_name":null,"funder_award_id":"31920240070","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"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W2018669440","https://openalex.org/W2101105183","https://openalex.org/W2150824314","https://openalex.org/W2194775991","https://openalex.org/W2506483933","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2890531016","https://openalex.org/W2963101956","https://openalex.org/W2983141445","https://openalex.org/W2986670728","https://openalex.org/W2997591391","https://openalex.org/W3035323998","https://openalex.org/W3091588028","https://openalex.org/W3093735614","https://openalex.org/W3110014757","https://openalex.org/W3135339232","https://openalex.org/W4291111171","https://openalex.org/W4385245566","https://openalex.org/W4385872197","https://openalex.org/W6638742206","https://openalex.org/W6678262379","https://openalex.org/W6763509872","https://openalex.org/W6791353385","https://openalex.org/W6803567076"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"To":[0],"address":[1],"the":[2,59,63,78,87,106,129,141,149,157,178,182],"challenges":[3],"of":[4,20,62,146,163],"insufficient":[5],"artistic":[6],"style":[7],"feature":[8,42,60,70,80,133],"extraction":[9],"in":[10,16,67,110,169,181],"Thangka":[11,37,68,102,115,150],"image":[12,38,41],"captioning":[13],"and":[14,31,167,173],"confusion":[15],"understanding":[17],"key":[18],"details":[19],"character":[21],"features":[22,89],"during":[23],"decoding,":[24],"we":[25,117],"propose":[26],"a":[27,50,54],"Region-Guided":[28],"Feature":[29],"Enhancement":[30],"Attribute":[32],"Prediction":[33],"(RGFEAP)":[34],"method":[35],"for":[36,101,114],"captioning.":[39],"The":[40],"enhancement":[43,71],"encoder,":[44],"based":[45],"on":[46,148],"region":[47],"guidance,":[48],"utilizes":[49],"region-guided":[51,142],"module":[52],"with":[53,86,161],"distance-weighted":[55],"strategy":[56],"to":[57,75,104,156,189],"enhance":[58,105],"representation":[61,108],"central":[64],"sacred":[65],"elements":[66],"images.AThangka":[69],"encoder":[72],"is":[73],"designed":[74],"further":[76],"refine":[77],"regional":[79],"vectors,":[81],"which":[82],"are":[83],"then":[84],"fused":[85],"global":[88],"extracted":[90],"by":[91,131],"CLIP":[92],"through":[93],"multi-scale":[94],"convolutional":[95,138],"fusion,":[96],"incorporating":[97],"richer":[98],"object-related":[99],"information":[100,127],"images.Furthermore,":[103],"detailed":[107,126],"capability":[109],"generating":[111],"long-sequence":[112],"captions":[113],"images,":[116],"design":[118],"an":[119],"attribute":[120],"predictor.":[121],"This":[122],"predictor":[123],"introduces":[124],"more":[125],"into":[128],"model":[130,159],"utilizing":[132],"maps":[134],"from":[135],"four":[136],"different":[137],"blocks":[139],"within":[140],"module.":[143],"Experimental":[144],"results":[145],"RGFEAP":[147,185],"dataset":[151,180],"demonstrate":[152],"significant":[153],"improvements":[154],"compared":[155],"baseline":[158],"ClipCap,":[160],"increases":[162],"14.0%,":[164],"17.7%,":[165],"185.7%,":[166],"11.5%":[168],"BLEU-1,":[170],"BLEU-4,":[171],"CIDEr,":[172],"METEOR":[174],"metrics,":[175],"respectively.":[176],"On":[177],"COCO":[179],"natural":[183],"domain,":[184],"achieves":[186],"comparable":[187],"performance":[188],"other":[190],"state-of-the-art":[191],"models,":[192],"showcasing":[193],"strong":[194],"adaptability.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}