{"id":"https://openalex.org/W3093088671","doi":"https://doi.org/10.1145/3394171.3413877","title":"Improving Intra- and Inter-Modality Visual Relation for Image Captioning","display_name":"Improving Intra- and Inter-Modality Visual Relation for Image Captioning","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093088671","doi":"https://doi.org/10.1145/3394171.3413877","mag":"3093088671"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5009822141","display_name":"Yong Wang","orcid":"https://orcid.org/0000-0003-1100-697X"},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]},{"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":"Yong Wang","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences & University of Chinese Academy of Sciences, beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences & University of Chinese Academy of Sciences, beijing, China","institution_ids":["https://openalex.org/I4210137199","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010612040","display_name":"WenKai Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210110458","display_name":"Institute of Electronics","ror":"https://ror.org/01z143507","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210110458"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"WenKai Zhang","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences & Institute of Electronics, Chinese Academy of Science, beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences & Institute of Electronics, Chinese Academy of Science, beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210110458","https://openalex.org/I4210137199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345183","display_name":"Qing Liu","orcid":"https://orcid.org/0000-0002-0592-171X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210110458","display_name":"Institute of Electronics","ror":"https://ror.org/01z143507","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210110458"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Liu","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences & Institute of Electronics, Chinese Academy of Science, beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences & Institute of Electronics, Chinese Academy of Science, beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210110458","https://openalex.org/I4210137199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714173","display_name":"Zhengyuan Zhang","orcid":"https://orcid.org/0000-0003-2383-7738"},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]},{"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":"Zhengyuan Zhang","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences & University of Chinese Academy of Sciences, beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences & University of Chinese Academy of Sciences, beijing, China","institution_ids":["https://openalex.org/I4210137199","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074960174","display_name":"Xin Gao","orcid":"https://orcid.org/0000-0001-9906-0596"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210110458","display_name":"Institute of Electronics","ror":"https://ror.org/01z143507","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210110458"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Gao","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences & Institute of Electronics, Chinese Academy of Science, beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences & Institute of Electronics, Chinese Academy of Science, beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210110458","https://openalex.org/I4210137199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005905514","display_name":"Xian Sun","orcid":"https://orcid.org/0000-0002-0038-9816"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210110458","display_name":"Institute of Electronics","ror":"https://ror.org/01z143507","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210110458"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Sun","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences & Institute of Electronics, Chinese Academy of Science, beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences & Institute of Electronics, Chinese Academy of Science, beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210110458","https://openalex.org/I4210137199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3669,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.87519151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4190","last_page":"4198"},"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":0.9991999864578247,"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":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7947702407836914},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7422932386398315},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.664820671081543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6266961693763733},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5553257465362549},{"id":"https://openalex.org/keywords/video-graphics-array","display_name":"Video Graphics Array","score":0.5463725328445435},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5445412397384644},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5037886500358582},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4770585596561432},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45896434783935547},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.432670533657074},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38459837436676025},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.17860612273216248}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7947702407836914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422932386398315},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.664820671081543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6266961693763733},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5553257465362549},{"id":"https://openalex.org/C139983466","wikidata":"https://www.wikidata.org/wiki/Q17194","display_name":"Video Graphics Array","level":3,"score":0.5463725328445435},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5445412397384644},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5037886500358582},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4770585596561432},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45896434783935547},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.432670533657074},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38459837436676025},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.17860612273216248},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2049705550","https://openalex.org/W2081613070","https://openalex.org/W2096733369","https://openalex.org/W2108598243","https://openalex.org/W2133564696","https://openalex.org/W2194775991","https://openalex.org/W2468907370","https://openalex.org/W2502312327","https://openalex.org/W2506483933","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2600463316","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2803525166","https://openalex.org/W2885013662","https://openalex.org/W2890531016","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963109634","https://openalex.org/W2963403868","https://openalex.org/W2964018924","https://openalex.org/W2968549119","https://openalex.org/W2979382951","https://openalex.org/W2983141445","https://openalex.org/W2984138079","https://openalex.org/W2986670728","https://openalex.org/W3099206234","https://openalex.org/W3101313921"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2360664843","https://openalex.org/W2364087260","https://openalex.org/W2390465755","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W4323777661","https://openalex.org/W4388184981","https://openalex.org/W3209117276"],"abstract_inverted_index":{"It":[0],"is":[1,83],"widely":[2],"shared":[3],"that":[4],"capturing":[5],"relationships":[6],"among":[7,36,58],"multi-modality":[8],"features":[9],"would":[10],"be":[11],"helpful":[12],"for":[13,49,120],"representing":[14],"and":[15,28],"ultimately":[16],"describing":[17],"an":[18,80],"image.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23,42,69],"present":[24],"a":[25],"novel":[26],"Intra-":[27],"Inter-modality":[29],"visual":[30,37,56],"Relation":[31,44],"Transformer":[32,46],"to":[33,61,85,103],"improve":[34],"connections":[35],"features,":[38],"termed":[39],"I2RT.":[40],"Firstly,":[41],"propose":[43],"Enhanced":[45],"Block":[47],"(RETB)":[48],"image":[50],"feature":[51,67],"learning,":[52],"which":[53],"strengthens":[54],"intra-modality":[55],"relations":[57],"objects.":[59],"Moreover,":[60],"bridge":[62],"the":[63,87,93,97,111,121,125],"gap":[64],"between":[65],"inter-modality":[66],"representations,":[68],"align":[70],"them":[71],"explicitly":[72],"via":[73],"Visual":[74],"Guided":[75],"Alignment":[76],"(VGA)":[77],"module.":[78],"Finally,":[79],"end-to-end":[81],"formulation":[82],"adopted":[84],"train":[86],"whole":[88],"model":[89],"jointly.":[90],"Experiments":[91],"on":[92,105,110],"MS-COCO":[94],"dataset":[95],"show":[96],"effectiveness":[98],"of":[99,124],"our":[100],"model,":[101],"leading":[102],"improvements":[104],"all":[106],"commonly":[107],"used":[108],"metrics":[109],"\"Karpathy\"":[112],"test":[113],"split.":[114],"Extensive":[115],"ablation":[116],"experiments":[117],"are":[118],"conducted":[119],"comprehensive":[122],"analysis":[123],"proposed":[126],"method.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}