{"id":"https://openalex.org/W4406457518","doi":"https://doi.org/10.1109/tip.2025.3528216","title":"Intra- and Inter-Head Orthogonal Attention for Image Captioning","display_name":"Intra- and Inter-Head Orthogonal Attention for Image Captioning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406457518","doi":"https://doi.org/10.1109/tip.2025.3528216","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030904"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3528216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3528216","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100356742","display_name":"Xiaodan Zhang","orcid":"https://orcid.org/0000-0001-7002-5447"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Zhang","raw_affiliation_strings":["College of Computer Science, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7002-5447","affiliations":[{"raw_affiliation_string":"College of Computer Science, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101451380","display_name":"Aozhe Jia","orcid":"https://orcid.org/0009-0004-9019-4087"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aozhe Jia","raw_affiliation_strings":["College of Computer Science, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-9019-4087","affiliations":[{"raw_affiliation_string":"College of Computer Science, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035117617","display_name":"Junzhong Ji","orcid":"https://orcid.org/0000-0001-6951-741X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhong Ji","raw_affiliation_strings":["College of Computer Science, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6951-741X","affiliations":[{"raw_affiliation_string":"College of Computer Science, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083630052","display_name":"Liangqiong Qu","orcid":"https://orcid.org/0000-0001-8235-7852"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Liangqiong Qu","raw_affiliation_strings":["School of Computing and Data Science, The University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-8235-7852","affiliations":[{"raw_affiliation_string":"School of Computing and Data Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015317495","display_name":"Qixiang Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qixiang Ye","raw_affiliation_strings":["School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1215-6259","affiliations":[{"raw_affiliation_string":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5932,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.94426494,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"34","issue":null,"first_page":"594","last_page":"607"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9965999722480774,"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":0.9887999892234802,"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":0.9089018702507019},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6566931009292603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6012279987335205},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5857205390930176},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5461233854293823},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5432461500167847},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.46430519223213196},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3369561433792114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3332463502883911}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9089018702507019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6566931009292603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6012279987335205},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5857205390930176},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5461233854293823},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5432461500167847},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.46430519223213196},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3369561433792114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3332463502883911},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2025.3528216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3528216","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:40030904","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030904","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":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:hub.hku.hk:10722/357522","is_oa":false,"landing_page_url":"https://hub.hku.hk/handle/10722/357522","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1072291470","display_name":null,"funder_award_id":"62276010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4100402671","display_name":null,"funder_award_id":"62306253","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6564926218","display_name":null,"funder_award_id":"2024A1515010233","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6735075065","display_name":null,"funder_award_id":"62225208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G89121010","display_name":null,"funder_award_id":"61906007","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W1497599070","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2302086703","https://openalex.org/W2506483933","https://openalex.org/W2550553598","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2799263800","https://openalex.org/W2890531016","https://openalex.org/W2946794439","https://openalex.org/W2949376505","https://openalex.org/W2962822108","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963406157","https://openalex.org/W2965697393","https://openalex.org/W2972324944","https://openalex.org/W2981165461","https://openalex.org/W2981748719","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W3034222740","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3035497460","https://openalex.org/W3039115681","https://openalex.org/W3103022576","https://openalex.org/W3167939936","https://openalex.org/W3174377922","https://openalex.org/W3175042876","https://openalex.org/W3205765769","https://openalex.org/W3212892036","https://openalex.org/W4213019668","https://openalex.org/W4214917601","https://openalex.org/W4226397058","https://openalex.org/W4280575403","https://openalex.org/W4282968790","https://openalex.org/W4283722434","https://openalex.org/W4286904641","https://openalex.org/W4312344082","https://openalex.org/W4313131769","https://openalex.org/W4320487288","https://openalex.org/W4321608137","https://openalex.org/W4385245566","https://openalex.org/W4386065386","https://openalex.org/W4388193026","https://openalex.org/W4388343614","https://openalex.org/W4388430331","https://openalex.org/W4389520712","https://openalex.org/W4390873420","https://openalex.org/W4393154592","https://openalex.org/W4404780983","https://openalex.org/W4405595839","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6730235532","https://openalex.org/W6733068669","https://openalex.org/W6762945437","https://openalex.org/W6763643401","https://openalex.org/W6791353385","https://openalex.org/W6801931546","https://openalex.org/W6849177959","https://openalex.org/W7064683377"],"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":{"Multi-head":[0],"attention":[1,46,88,103,147],"(MA),":[2],"which":[3,99,122],"allows":[4],"the":[5,87,101,113,124,131,137,154,164,169,172],"model":[6,158],"to":[7,10,33,37,67,80,96,104,142],"jointly":[8],"attend":[9],"crucial":[11],"information":[12],"from":[13],"diverse":[14,41],"representation":[15,127,132],"subspaces":[16,128],"through":[17],"its":[18],"heads,":[19,121],"has":[20],"yielded":[21],"remarkable":[22],"achievement":[23],"in":[24,40,44,71],"image":[25,72,149],"captioning.":[26],"However,":[27],"there":[28],"is":[29,140],"no":[30],"explicit":[31],"mechanism":[32],"ensure":[34],"MA":[35,70,91],"attends":[36],"appropriate":[38],"positions":[39],"subspaces,":[42],"resulting":[43],"overfocused":[45],"for":[47,134],"each":[48,97],"head":[49],"and":[50,62,129,152,160],"redundancy":[51,115],"between":[52,120],"heads.":[53,81],"In":[54],"this":[55],"paper,":[56],"we":[57],"propose":[58],"a":[59,76],"novel":[60],"Intra-":[61],"Inter-Head":[63,109],"Orthogonal":[64,84,110],"Attention":[65,85,111],"(I2OA)":[66],"efficiently":[68],"improve":[69,153],"captioning":[73,150],"by":[74,92,116],"introducing":[75,93],"concise":[77],"orthogonal":[78,94,118],"regularization":[79],"Specifically,":[82],"Intra-Head":[83],"enhances":[86],"learning":[89],"of":[90,126,171],"constraint":[95,119],"head,":[98],"decentralizes":[100],"object-centric":[102],"more":[105],"comprehensive":[106],"content-aware":[107],"attention.":[108],"reduces":[112],"heads":[114],"applying":[117],"enlarges":[123],"diversity":[125],"improves":[130],"ability":[133],"MA.":[135],"Moreover,":[136],"proposed":[138,173],"I2OA":[139],"flexible":[141],"combine":[143],"with":[144],"various":[145],"multi-head":[146],"based":[148],"methods":[151],"performances":[155],"without":[156],"increasing":[157],"complexity":[159],"parameters.":[161],"Experiments":[162],"on":[163],"MS":[165],"COCO":[166],"dataset":[167],"demonstrate":[168],"effectiveness":[170],"model.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}