{"id":"https://openalex.org/W2955014993","doi":"https://doi.org/10.1109/tpami.2019.2926266","title":"Variational Context: Exploiting Visual and Textual Context for Grounding Referring Expressions","display_name":"Variational Context: Exploiting Visual and Textual Context for Grounding Referring Expressions","publication_year":2019,"publication_date":"2019-07-07","ids":{"openalex":"https://openalex.org/W2955014993","doi":"https://doi.org/10.1109/tpami.2019.2926266","mag":"2955014993","pmid":"https://pubmed.ncbi.nlm.nih.gov/31283493"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2019.2926266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2019.2926266","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.03609","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028589167","display_name":"Yulei Niu","orcid":"https://orcid.org/0000-0001-6332-3382"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulei Niu","raw_affiliation_strings":["School of Information & Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information & Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103244144","display_name":"Zhiwu Lu","orcid":"https://orcid.org/0000-0001-6429-7956"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwu Lu","raw_affiliation_strings":["School of Information & Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information & Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037340457","display_name":"Shih\u2010Fu Chang","orcid":"https://orcid.org/0000-0003-1444-1205"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shih-Fu Chang","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3895,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.8516923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"43","issue":"1","first_page":"1","last_page":"1"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9969000220298767,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9940999746322632,"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/referent","display_name":"Referent","score":0.8647881150245667},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6901823282241821},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6764437556266785},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5875971913337708},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5471420288085938},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.5113224983215332},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.46748751401901245},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4504399001598358},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.4311593770980835},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34298619627952576},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3337748348712921},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08470737934112549}],"concepts":[{"id":"https://openalex.org/C2777096784","wikidata":"https://www.wikidata.org/wiki/Q3826351","display_name":"Referent","level":2,"score":0.8647881150245667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6901823282241821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6764437556266785},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5875971913337708},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5471420288085938},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.5113224983215332},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.46748751401901245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4504399001598358},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.4311593770980835},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34298619627952576},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3337748348712921},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08470737934112549},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2019.2926266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2019.2926266","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:31283493","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31283493","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 pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:1907.03609","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.03609","pdf_url":"https://arxiv.org/pdf/1907.03609","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.03609","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.03609","pdf_url":"https://arxiv.org/pdf/1907.03609","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2565448097","display_name":null,"funder_award_id":"61573363","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3634295602","display_name":null,"funder_award_id":"61832017","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":89,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W15689187","https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1533861849","https://openalex.org/W1533917153","https://openalex.org/W1543294385","https://openalex.org/W1773149199","https://openalex.org/W1836465849","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W1959608418","https://openalex.org/W2005814556","https://openalex.org/W2110119381","https://openalex.org/W2119717200","https://openalex.org/W2125447031","https://openalex.org/W2128248292","https://openalex.org/W2131774270","https://openalex.org/W2133564696","https://openalex.org/W2136634080","https://openalex.org/W2156718681","https://openalex.org/W2188365844","https://openalex.org/W2247513039","https://openalex.org/W2250378130","https://openalex.org/W2250539671","https://openalex.org/W2250799982","https://openalex.org/W2251512949","https://openalex.org/W2463565445","https://openalex.org/W2479423890","https://openalex.org/W2489434015","https://openalex.org/W2554334383","https://openalex.org/W2558535589","https://openalex.org/W2570343428","https://openalex.org/W2571175805","https://openalex.org/W2583360688","https://openalex.org/W2591644541","https://openalex.org/W2600144439","https://openalex.org/W2603266952","https://openalex.org/W2605736949","https://openalex.org/W2607855566","https://openalex.org/W2609468337","https://openalex.org/W2613718673","https://openalex.org/W2623594919","https://openalex.org/W2741903908","https://openalex.org/W2770129969","https://openalex.org/W2779827764","https://openalex.org/W2799263800","https://openalex.org/W2904164128","https://openalex.org/W2912274075","https://openalex.org/W2950761309","https://openalex.org/W2962764817","https://openalex.org/W2963042258","https://openalex.org/W2963109634","https://openalex.org/W2963224792","https://openalex.org/W2963547393","https://openalex.org/W2963567641","https://openalex.org/W2963668159","https://openalex.org/W2963735856","https://openalex.org/W2963976294","https://openalex.org/W2963980128","https://openalex.org/W2964036520","https://openalex.org/W2964199361","https://openalex.org/W2964284374","https://openalex.org/W2964308564","https://openalex.org/W2964345792","https://openalex.org/W3098232790","https://openalex.org/W3106250896","https://openalex.org/W4241811150","https://openalex.org/W4289126595","https://openalex.org/W4293568373","https://openalex.org/W6600628944","https://openalex.org/W6620707391","https://openalex.org/W6630875275","https://openalex.org/W6631943919","https://openalex.org/W6632089592","https://openalex.org/W6638667902","https://openalex.org/W6639102338","https://openalex.org/W6640963894","https://openalex.org/W6679434410","https://openalex.org/W6682888085","https://openalex.org/W6687045409","https://openalex.org/W6691783751","https://openalex.org/W6719057275","https://openalex.org/W6720244596","https://openalex.org/W6730039040","https://openalex.org/W6757135208","https://openalex.org/W6780248173","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W97399927","https://openalex.org/W2140435402","https://openalex.org/W4285276086","https://openalex.org/W2161633202","https://openalex.org/W2039787362","https://openalex.org/W2901621883","https://openalex.org/W1750537857","https://openalex.org/W2163490908","https://openalex.org/W3022564861","https://openalex.org/W2394987862"],"abstract_inverted_index":{"We":[0,181],"focus":[1],"on":[2,177,199],"grounding":[3],"(i.e.,":[4],"localizing":[5],"or":[6],"linking)":[7],"referring":[8,118,171],"expressions":[9],"in":[10,75,117,208],"images,":[11],"e.g.,":[12],"\"largest":[13],"elephant":[14],"standing":[15],"behind":[16],"baby":[17],"elephant\".":[18],"This":[19],"is":[20,195],"a":[21,102],"general":[22],"yet":[23],"challenging":[24],"vision-language":[25],"task":[26,88],"since":[27],"it":[28],"does":[29],"not":[30],"only":[31],"require":[32],"the":[33,39,58,66,71,77,111,125,129,140,144,148,164,170,178,184,193],"localization":[34],"of":[35,42,65,113,135,139,143,151,167],"objects,":[36,62],"but":[37],"also":[38,182],"multimodal":[40],"comprehension":[41],"context":[43,78,115,152],"-":[44],"visual":[45],"attributes":[46],"(e.g.,":[47,52],"\"largest\",":[48],"\"baby\")":[49],"and":[50,131,146,211],"relationships":[51],"\"behind\")":[53],"that":[54],"help":[55],"to":[56,70,89,109,159,186],"distinguish":[57],"referent":[59,130,194],"from":[60],"other":[61],"especially":[63],"those":[64],"same":[67],"category.":[68],"Due":[69],"exponential":[72],"complexity":[73],"involved":[74],"modeling":[76,92,116],"associated":[79],"with":[80],"multiple":[81,94],"image":[82],"regions,":[83],"existing":[84],"work":[85],"oversimplifies":[86],"this":[87,98],"pairwise":[90],"region":[91],"by":[93],"instance":[95],"learning.":[96],"In":[97,157],"paper,":[99],"we":[100],"propose":[101],"variational":[103],"Bayesian":[104],"method,":[105],"called":[106],"Variational":[107],"Context,":[108],"solve":[110],"problem":[112],"complex":[114],"expression":[119,172],"grounding.":[120],"Specifically,":[121],"our":[122,161],"framework":[123,162],"exploits":[124],"reciprocal":[126],"relation":[127],"between":[128],"context,":[132,168],"i.e.,":[133,169],"either":[134],"them":[136],"influences":[137],"estimation":[138],"posterior":[141],"distribution":[142],"other,":[145],"thereby":[147],"search":[149],"space":[150],"can":[153,173],"be":[154,174],"greatly":[155],"reduced.":[156],"addition":[158],"reciprocity,":[160],"considers":[163],"semantic":[165],"information":[166],"reproduced":[175],"based":[176],"estimated":[179],"context.":[180],"extend":[183],"model":[185],"unsupervised":[187,212],"setting":[188],"where":[189],"no":[190],"annotation":[191],"for":[192],"available.":[196],"Extensive":[197],"experiments":[198],"various":[200],"benchmarks":[201],"show":[202],"consistent":[203],"improvement":[204],"over":[205],"state-of-the-art":[206],"methods":[207],"both":[209],"supervised":[210],"settings.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}