{"id":"https://openalex.org/W2949554687","doi":"https://doi.org/10.18653/v1/p19-1182","title":"Expressing Visual Relationships via Language","display_name":"Expressing Visual Relationships via Language","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2949554687","doi":"https://doi.org/10.18653/v1/p19-1182","mag":"2949554687"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1182","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1182","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/p19-1182","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074267258","display_name":"Hao Tan","orcid":"https://orcid.org/0000-0002-9489-6543"},"institutions":[{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]},{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Tan","raw_affiliation_strings":["UNC Chapel Hill","Adobe Research"],"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I1333535994","https://openalex.org/I114027177"]},{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028863551","display_name":"Franck Dernoncourt","orcid":"https://orcid.org/0000-0002-1119-1346"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franck Dernoncourt","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564904","display_name":"Zhe Lin","orcid":"https://orcid.org/0000-0003-1154-9907"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Lin","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113663962","display_name":"Trung Bui","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trung Bui","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001987532","display_name":"Mohit Bansal","orcid":"https://orcid.org/0000-0001-5522-1351"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohit Bansal","raw_affiliation_strings":["UNC Chapel Hill"],"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I1333535994","https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5074267258"],"corresponding_institution_ids":["https://openalex.org/I1333535994","https://openalex.org/I114027177","https://openalex.org/I1306409833"],"apc_list":null,"apc_paid":null,"fwci":2.13771515,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.89669158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1873","last_page":"1883"},"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":0.9828000068664551,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9797999858856201,"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":0.898051381111145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.883770763874054},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6272169947624207},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5852731466293335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5753352046012878},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5720848441123962},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5680720806121826},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.5677980780601501},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5085040330886841},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4821609854698181},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.47098347544670105},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1283285915851593}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.898051381111145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.883770763874054},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6272169947624207},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5852731466293335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5753352046012878},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5720848441123962},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5680720806121826},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.5677980780601501},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5085040330886841},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4821609854698181},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47098347544670105},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1283285915851593},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1182","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1182","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1182","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1182","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2133564696","https://openalex.org/W2139501017","https://openalex.org/W2144960104","https://openalex.org/W2154652894","https://openalex.org/W2176263492","https://openalex.org/W2194775991","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2425121537","https://openalex.org/W2561715562","https://openalex.org/W2563399268","https://openalex.org/W2564590796","https://openalex.org/W2571175805","https://openalex.org/W2574790321","https://openalex.org/W2583360688","https://openalex.org/W2607059968","https://openalex.org/W2745461083","https://openalex.org/W2779827764","https://openalex.org/W2897946384","https://openalex.org/W2949376505","https://openalex.org/W2951293099","https://openalex.org/W2962749469","https://openalex.org/W2962937869","https://openalex.org/W2963084599","https://openalex.org/W2963109634","https://openalex.org/W2963145877","https://openalex.org/W2963248296","https://openalex.org/W2963318456","https://openalex.org/W2963385935","https://openalex.org/W2963403868","https://openalex.org/W2963448089","https://openalex.org/W2963502052","https://openalex.org/W2963530300","https://openalex.org/W2963843052","https://openalex.org/W2963976294","https://openalex.org/W2964183327","https://openalex.org/W2964196083","https://openalex.org/W2964245290","https://openalex.org/W2964308564","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/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Describing":[0],"images":[1],"with":[2,87,104,117,144],"text":[3],"is":[4],"a":[5,72,80,94],"fundamental":[6],"problem":[7,47],"in":[8,13,23,66],"vision-language":[9],"research.":[10],"Current":[11],"studies":[12],"this":[14,67],"domain":[15],"mostly":[16,52],"focus":[17],"on":[18,100,131,150,166],"single":[19],"image":[20,28,75,85,141],"captioning.":[21],"However,":[22],"various":[24],"real":[25,84],"applications":[26],"(e.g.,":[27],"editing,":[29],"difference":[30],"interpretation,":[31],"and":[32,58,108,135,153,163],"retrieval),":[33],"generating":[34],"relational":[35,96,106,119],"captions":[36],"for":[37],"two":[38,136],"images,":[39],"can":[40],"also":[41,113],"be":[42],"very":[43],"useful.":[44],"This":[45],"important":[46],"has":[48],"not":[49],"been":[50],"explored":[51],"due":[53],"to":[54],"lack":[55],"of":[56,83,140],"datasets":[57,138],"effective":[59],"models.":[60],"To":[61],"push":[62],"forward":[63],"the":[64,115,168],"research":[65],"direction,":[68],"we":[69],"first":[70],"introduce":[71],"new":[73,95],"language-guided":[74],"editing":[76,89],"dataset":[77],"that":[78,157],"contains":[79],"large":[81],"number":[82],"pairs":[86,142],"corresponding":[88],"instructions.":[90],"We":[91,112],"then":[92],"propose":[93],"speaker":[97],"model":[98,116,159],"based":[99,149],"an":[101],"encoder-decoder":[102],"architecture":[103],"static":[105],"attention":[107],"sequential":[109],"multi-head":[110],"attention.":[111],"extend":[114],"dynamic":[118],"attention,":[120],"which":[121],"calculates":[122],"visual":[123],"alignment":[124],"while":[125],"decoding.":[126],"Our":[127],"models":[128],"are":[129],"evaluated":[130],"our":[132,158],"newly":[133],"collected":[134],"public":[137],"consisting":[139],"annotated":[143],"relationship":[145],"sentences.":[146],"Experimental":[147],"results,":[148],"both":[151],"automatic":[152],"human":[154],"evaluation,":[155],"demonstrate":[156],"outperforms":[160],"all":[161,167],"baselines":[162],"existing":[164],"methods":[165],"datasets.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}