{"id":"https://openalex.org/W2981587852","doi":"https://doi.org/10.1145/3343031.3351063","title":"Referring Expression Comprehension with Semantic Visual Relationship and Word Mapping","display_name":"Referring Expression Comprehension with Semantic Visual Relationship and Word Mapping","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981587852","doi":"https://doi.org/10.1145/3343031.3351063","mag":"2981587852"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3351063","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th 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/A5100460297","display_name":"Chao Zhang","orcid":"https://orcid.org/0009-0007-2579-8783"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Samsung Research China, Chaoyang, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research China, Chaoyang, Beijing, China","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695259","display_name":"Weiming Li","orcid":"https://orcid.org/0000-0002-6605-8905"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Li","raw_affiliation_strings":["Samsung Research China, Chaoyang, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research China, Chaoyang, Beijing, China","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087818121","display_name":"Wanli Ouyang","orcid":"https://orcid.org/0000-0002-9163-2761"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wanli Ouyang","raw_affiliation_strings":["The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709541","display_name":"Qiang Wang","orcid":"https://orcid.org/0000-0001-5632-4408"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Wang","raw_affiliation_strings":["Samsung Research China, Chaoyang, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research China, Chaoyang, Beijing, China","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103265754","display_name":"Woo-Shik Kim","orcid":"https://orcid.org/0000-0002-3345-1137"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woo-Shik Kim","raw_affiliation_strings":["Samsung Advanced Institute of Technology, Suwon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074116974","display_name":"Sung\u2010Hoon Hong","orcid":"https://orcid.org/0000-0002-3408-2820"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sunghoon Hong","raw_affiliation_strings":["Samsung Advanced Institute of Technology, Suwon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1258","last_page":"1266"},"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":0.9932000041007996,"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":0.987500011920929,"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/computer-science","display_name":"Computer science","score":0.8251596689224243},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7504875659942627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7102369070053101},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.6051939725875854},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5754438042640686},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5557260513305664},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5378922820091248},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5315181016921997},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5273034572601318},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5197015404701233},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.5185607075691223},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4697461724281311},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.45725175738334656},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.44510388374328613},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.4194547235965729},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.195298969745636},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16538381576538086},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.16022971272468567},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0816393494606018}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251596689224243},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7504875659942627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7102369070053101},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.6051939725875854},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5754438042640686},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5557260513305664},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5378922820091248},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5315181016921997},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5273034572601318},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5197015404701233},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.5185607075691223},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4697461724281311},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.45725175738334656},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.44510388374328613},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4194547235965729},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.195298969745636},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16538381576538086},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.16022971272468567},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0816393494606018},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3351063","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7099999785423279,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1892016050","https://openalex.org/W1969616664","https://openalex.org/W2077069816","https://openalex.org/W2153579005","https://openalex.org/W2160254296","https://openalex.org/W2193145675","https://openalex.org/W2247513039","https://openalex.org/W2489434015","https://openalex.org/W2552161745","https://openalex.org/W2558535589","https://openalex.org/W2560920409","https://openalex.org/W2571175805","https://openalex.org/W2583360688","https://openalex.org/W2613718673","https://openalex.org/W2779827764","https://openalex.org/W2810482788","https://openalex.org/W2963037989","https://openalex.org/W2963109634","https://openalex.org/W2963224792","https://openalex.org/W2963389687","https://openalex.org/W2963649796","https://openalex.org/W2963735856","https://openalex.org/W2964118342","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W3098232790","https://openalex.org/W3106250896","https://openalex.org/W4301409532"],"related_works":["https://openalex.org/W2980729574","https://openalex.org/W2510877880","https://openalex.org/W2118130975","https://openalex.org/W2375044702","https://openalex.org/W2389814472","https://openalex.org/W2375810704","https://openalex.org/W2006987377","https://openalex.org/W1827099466","https://openalex.org/W2770296245","https://openalex.org/W4365503698"],"abstract_inverted_index":{"Referring":[0],"expression":[1,78,195],"comprehension,":[2],"which":[3],"locates":[4],"the":[5,25,46,56,71,76,84,91,118,124,131,139,185],"object":[6,60,86],"instance":[7],"described":[8],"by":[9],"a":[10,98,113,163],"natural":[11],"language":[12,34,77,110],"expression,":[13],"gains":[14],"increasing":[15],"interests":[16],"in":[17,90,123,138],"recent":[18],"years.":[19],"This":[20,69],"paper":[21],"aims":[22],"at":[23],"improving":[24],"task":[26],"from":[27,87,117],"two":[28],"aspects:":[29],"visual":[30,38,57],"feature":[31,39,111],"extraction":[32],"and":[33],"features":[35],"extraction.":[36],"For":[37,109],"extraction,":[40,112],"we":[41,96,161],"observe":[42],"that":[43,169,184],"most":[44],"of":[45,121,130],"previous":[47],"methods":[48,191],"utilize":[49],"only":[50],"relative":[51],"spatial":[52],"information":[53],"to":[54,82,104,148,150,175],"model":[55],"relationship":[58,66,81],"between":[59,67],"pairs":[61],"while":[62],"discarding":[63],"rich":[64],"semantic":[65,80],"objects.":[68],"makes":[70],"visual-language":[72],"matching":[73],"difficult":[74],"when":[75],"contains":[79],"discriminate":[83],"referred":[85],"other":[88],"objects":[89],"image.":[92],"In":[93],"this":[94,106,159],"work,":[95],"propose":[97,162],"Semantic":[99],"Visual":[100],"Relationship":[101],"Module":[102],"(SVRM)":[103],"exploit":[105],"important":[107],"information.":[108],"major":[114],"problem":[115],"comes":[116],"long-tail":[119],"distribution":[120],"words":[122,132,174,178],"expressions.":[125],"Since":[126],"more":[127],"than":[128,135],"half":[129],"appear":[133],"less":[134],"20":[136],"times":[137],"public":[140],"datasets,":[141],"deep":[142],"models":[143],"such":[144],"as":[145],"LSTM":[146],"tend":[147],"fail":[149],"learn":[151],"accurate":[152],"representations":[153],"for":[154],"these":[155,171],"words.":[156],"To":[157],"solve":[158],"problem,":[160],"word2vec":[164],"based":[165],"word":[166],"mapping":[167],"method":[168,187],"maps":[170],"low":[172],"frequency":[173,177],"high":[176],"with":[179],"similar":[180],"meaning.":[181],"Experiments":[182],"show":[183],"proposed":[186],"outperforms":[188],"existing":[189],"state-of-the-art":[190],"on":[192],"three":[193],"referring":[194],"comprehension":[196],"datasets.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}