{"id":"https://openalex.org/W2978431291","doi":"https://doi.org/10.1109/ijcnn.2019.8851832","title":"Visual Relationship Attention for Image Captioning","display_name":"Visual Relationship Attention for Image Captioning","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2978431291","doi":"https://doi.org/10.1109/ijcnn.2019.8851832","mag":"2978431291"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8851832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5060113731","display_name":"Zongjian Zhang","orcid":"https://orcid.org/0000-0001-9309-1826"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Zongjian Zhang","raw_affiliation_strings":["School of Electrical and Data Engineering, University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Data Engineering, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714578","display_name":"Yang Wang","orcid":"https://orcid.org/0000-0002-6815-0879"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["School of Software, University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Software, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063629854","display_name":"Qiang Wu","orcid":"https://orcid.org/0000-0001-5641-2483"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiang Wu","raw_affiliation_strings":["School of Electrical and Data Engineering, University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Data Engineering, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100400043","display_name":"Fang Chen","orcid":"https://orcid.org/0000-0003-4971-8729"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Fang Chen","raw_affiliation_strings":["School of Software, University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Software, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060113731"],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":0.4089,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66077031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9965999722480774,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9908999800682068,"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":0.9679084420204163},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7871888875961304},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6667517423629761},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6205079555511475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5742611885070801},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.5032021403312683},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.500723123550415},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.45522981882095337},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4124464988708496},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4074844717979431},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3638843894004822},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.11417382955551147},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10960844159126282},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07014116644859314}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9679084420204163},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7871888875961304},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6667517423629761},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6205079555511475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5742611885070801},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.5032021403312683},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.500723123550415},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.45522981882095337},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4124464988708496},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4074844717979431},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3638843894004822},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.11417382955551147},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10960844159126282},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07014116644859314},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn.2019.8851832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/139133","is_oa":false,"landing_page_url":"http://hdl.handle.net/10453/139133","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1924770834","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2560645892","https://openalex.org/W2563296158","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2753232960","https://openalex.org/W2754927243","https://openalex.org/W2802194751","https://openalex.org/W2885013662","https://openalex.org/W2890531016","https://openalex.org/W2962760898","https://openalex.org/W2962835968","https://openalex.org/W2963076818","https://openalex.org/W2963084599","https://openalex.org/W2963630207","https://openalex.org/W2963703618","https://openalex.org/W2963758027","https://openalex.org/W2963858333","https://openalex.org/W2963954913","https://openalex.org/W2964015378","https://openalex.org/W2964018924","https://openalex.org/W2964121744","https://openalex.org/W2964145825","https://openalex.org/W4297733535","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6640212811","https://openalex.org/W6694395031","https://openalex.org/W6713582119","https://openalex.org/W6714414533","https://openalex.org/W6726873649","https://openalex.org/W6728925852","https://openalex.org/W6742999658","https://openalex.org/W6743446608","https://openalex.org/W6747795875"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949362007","https://openalex.org/W2895420168"],"abstract_inverted_index":{"Visual":[0],"attention":[1,72,78,107,111,145],"mechanisms":[2],"have":[3],"been":[4],"broadly":[5],"used":[6],"by":[7],"image":[8,20,49,122],"captioning":[9,123],"models":[10],"to":[11,13,29,112,114],"attend":[12,113],"related":[14,115,149],"visual":[15,35,45,70,91,105,109,116,143,150],"information":[16,47,89],"dynamically,":[17],"allowing":[18],"fine-grained":[19],"understanding":[21],"and":[22,37,93,95,108,118,136,152],"reasoning.":[23],"However,":[24],"they":[25],"are":[26],"only":[27],"designed":[28],"discover":[30],"the":[31,38,76,81,98,130,155],"region-level":[32],"alignment":[33,100],"between":[34,48,101],"features":[36],"language":[39,94],"feature.":[40],"The":[41],"exploration":[42],"of":[43],"higher-level":[44],"relationship":[46,71,88,106,144,151],"regions,":[50],"which":[51],"is":[52,58],"rarely":[53],"researched":[54],"in":[55],"recent":[56],"works,":[57],"beyond":[59],"their":[60],"capabilities.":[61],"To":[62],"fill":[63],"this":[64],"gap,":[65],"we":[66],"propose":[67],"a":[68],"novel":[69,142],"model":[73,124,146],"based":[74],"on":[75,129],"parallel":[77],"mechanism":[79],"under":[80],"learnt":[82],"spatial":[83],"constraints.":[84],"It":[85],"can":[86,125,147],"extract":[87],"from":[90],"regions":[92,119],"then":[96],"achieve":[97,126],"relationship-level":[99],"them.":[102],"Using":[103],"combined":[104],"region":[110],"relationships":[117],"respectively,":[120],"our":[121,141],"state-of-the-art":[127],"performances":[128],"MSCOCO":[131],"dataset.":[132],"Both":[133],"quantitative":[134],"analysis":[135,138],"qualitative":[137],"demonstrate":[139],"that":[140],"capture":[148],"further":[153],"improve":[154],"caption":[156],"quality.":[157]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}