{"id":"https://openalex.org/W4285606316","doi":"https://doi.org/10.24963/ijcai.2022/151","title":"ER-SAN: Enhanced-Adaptive Relation Self-Attention Network for Image Captioning","display_name":"ER-SAN: Enhanced-Adaptive Relation Self-Attention Network for Image Captioning","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285606316","doi":"https://doi.org/10.24963/ijcai.2022/151"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/151","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/151","pdf_url":"https://www.ijcai.org/proceedings/2022/0151.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0151.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019056579","display_name":"Jingyu Li","orcid":"https://orcid.org/0000-0002-5172-010X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingyu Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023341829","display_name":"Zhendong Mao","orcid":"https://orcid.org/0000-0001-5739-8126"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhendong Mao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008604905","display_name":"Shancheng Fang","orcid":"https://orcid.org/0000-0002-3100-3664"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shancheng Fang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105008420","display_name":"Hao Li","orcid":"https://orcid.org/0009-0003-9621-0925"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019056579"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.8851,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.82210549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1081","last_page":"1087"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9908000230789185,"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":0.7670931816101074},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7600481510162354},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6805971264839172},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.6018015146255493},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5441824197769165},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5072169303894043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4727921187877655},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4332500100135803},{"id":"https://openalex.org/keywords/semantic-property","display_name":"Semantic property","score":0.43306082487106323},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3903936743736267},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.38469386100769043},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.15481287240982056}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7670931816101074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7600481510162354},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6805971264839172},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.6018015146255493},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5441824197769165},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5072169303894043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4727921187877655},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4332500100135803},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.43306082487106323},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3903936743736267},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38469386100769043},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.15481287240982056},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/151","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/151","pdf_url":"https://www.ijcai.org/proceedings/2022/0151.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/151","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/151","pdf_url":"https://www.ijcai.org/proceedings/2022/0151.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1143620254","display_name":null,"funder_award_id":"2021M693092","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G5198023733","display_name":null,"funder_award_id":"2020YFB1406603","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8384397740","display_name":null,"funder_award_id":"No. 2021M693092","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G891989852","display_name":null,"funder_award_id":"62102384","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/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285606316.pdf","grobid_xml":"https://content.openalex.org/works/W4285606316.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W2123301721","https://openalex.org/W2481240925","https://openalex.org/W2506483933","https://openalex.org/W2745461083","https://openalex.org/W2964015378","https://openalex.org/W2986670728","https://openalex.org/W2990069284","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3036790639","https://openalex.org/W3167939936","https://openalex.org/W3174377922","https://openalex.org/W3191818374","https://openalex.org/W3205607545","https://openalex.org/W4288329833","https://openalex.org/W4289542422","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661"],"abstract_inverted_index":{"Image":[0],"captioning":[1],"(IC),":[2],"bringing":[3],"vision":[4],"to":[5,56,59,74,87,132,138,142,166,187],"language,":[6],"has":[7],"drawn":[8],"extensive":[9],"attention.":[10],"Precisely":[11],"describing":[12],"visual":[13,28,64],"relations":[14,134,137],"between":[15,49,91],"image":[16],"objects":[17,92,131,140],"is":[18,31,72],"a":[19,94,115],"key":[20],"challenge":[21],"in":[22],"IC.":[23],"We":[24,122],"argue":[25],"that":[26,30,97,155],"the":[27,46,61,69,77,89,124,176],"relations,":[29,65,104],"geometric":[32,57,71,103,161],"positions":[33,58],"(i.e.,":[34,41],"distance":[35],"and":[36,38,43,79,102,135,160],"size)":[37],"semantic":[39,101,133,136,159],"interactions":[40],"actions":[42],"possessives),":[44],"indicate":[45],"mutual":[47],"correlations":[48,90],"objects.":[50],"Existing":[51],"Transformer-based":[52],"methods":[53],"typically":[54],"resort":[55],"enhance":[60,88],"representation":[62],"of":[63,178,183],"yet":[66],"only":[67],"using":[68],"shallow":[70],"unable":[73],"precisely":[75],"cover":[76],"complex":[78],"actional":[80],"correlations.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85,113,148],"propose":[86,114],"from":[93,185],"comprehensive":[95],"view":[96],"jointly":[98],"considers":[99,129],"explicit":[100,144],"generating":[105],"plausible":[106],"captions":[107],"with":[108,181],"accurate":[109],"relationship":[110],"predictions.":[111],"Specifically,":[112],"novel":[116],"Enhanced-Adaptive":[117],"Relation":[118],"Self-Attention":[119],"Network":[120],"(ER-SAN).":[121],"design":[123],"direction-sensitive":[125],"semantic-enhanced":[126],"attention,":[127],"which":[128],"content":[130,139],"attention":[141,162],"learn":[143],"semantic-aware":[145],"relations.":[146],"Further,":[147],"devise":[149],"an":[150],"adaptive":[151],"re-weight":[152],"relation":[153,168],"module":[154],"determines":[156],"how":[157],"much":[158],"should":[163],"be":[164,194],"activated":[165],"each":[167],"feature.":[169],"Extensive":[170],"experiments":[171],"on":[172],"MS-COCO":[173],"dataset":[174],"demonstrate":[175],"effectiveness":[177],"our":[179],"ER-SAN,":[180],"improvements":[182],"CIDEr":[184],"128.6%":[186],"135.3%,":[188],"achieving":[189],"state-of-the-art":[190],"performance.":[191],"Codes":[192],"will":[193],"released":[195],"\\url{https://github.com/CrossmodalGroup/ER-SAN}.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}