{"id":"https://openalex.org/W2981951787","doi":"https://doi.org/10.1145/3343031.3351055","title":"Cross-Modal Image-Text Retrieval with Semantic Consistency","display_name":"Cross-Modal Image-Text Retrieval with Semantic Consistency","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981951787","doi":"https://doi.org/10.1145/3343031.3351055","mag":"2981951787"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3351055","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351055","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/A5100334151","display_name":"Hui Chen","orcid":"https://orcid.org/0000-0001-9326-6649"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057732142","display_name":"Guiguang Ding","orcid":"https://orcid.org/0000-0003-0137-9975"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiguang Ding","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077882811","display_name":"Zijia Lin","orcid":"https://orcid.org/0000-0002-1390-7424"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijia Lin","raw_affiliation_strings":["Microsoft Research, Beijng, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijng, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051149140","display_name":"Sicheng Zhao","orcid":"https://orcid.org/0000-0001-5843-6411"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sicheng Zhao","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046605531","display_name":"Jungong Han","orcid":"https://orcid.org/0000-0003-4361-956X"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jungong Han","raw_affiliation_strings":["University of Warwick, Coventry, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Warwick, Coventry, United Kingdom","institution_ids":["https://openalex.org/I39555362"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1749","last_page":"1757"},"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":0.9987999796867371,"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/embedding","display_name":"Embedding","score":0.8364142179489136},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7167538404464722},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7021658420562744},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5617062449455261},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.492527574300766},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.46912240982055664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4473143517971039},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4460309147834778},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44146865606307983},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.44062063097953796},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.44006574153900146},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.324904203414917}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8364142179489136},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7167538404464722},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7021658420562744},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5617062449455261},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.492527574300766},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.46912240982055664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4473143517971039},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4460309147834778},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44146865606307983},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.44062063097953796},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.44006574153900146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.324904203414917},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3351055","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351055","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":[{"score":0.5099999904632568,"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":34,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W1905882502","https://openalex.org/W1916445035","https://openalex.org/W1922199343","https://openalex.org/W2086958058","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2123024445","https://openalex.org/W2153579005","https://openalex.org/W2157331557","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2493916176","https://openalex.org/W2508487189","https://openalex.org/W2512032049","https://openalex.org/W2526152041","https://openalex.org/W2546696630","https://openalex.org/W2552579943","https://openalex.org/W2613718673","https://openalex.org/W2741168003","https://openalex.org/W2745461083","https://openalex.org/W2765440071","https://openalex.org/W2774596107","https://openalex.org/W2778940641","https://openalex.org/W2798782720","https://openalex.org/W2899771611","https://openalex.org/W2950178297","https://openalex.org/W2951002515","https://openalex.org/W2962964995","https://openalex.org/W2963040148","https://openalex.org/W2963403868","https://openalex.org/W2963467339","https://openalex.org/W2963626623","https://openalex.org/W2964120214"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2188500270","https://openalex.org/W2303858293","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W2798198862","https://openalex.org/W2915512527","https://openalex.org/W51364034","https://openalex.org/W1546381263"],"abstract_inverted_index":{"Cross-modal":[0],"image-text":[1,27],"retrieval":[2],"has":[3],"been":[4],"a":[5,25,89],"long-standing":[6],"challenge":[7],"in":[8,93],"the":[9,21,33,43,57,69,74,94,137,148,153],"multimedia":[10],"community.":[11],"Existing":[12],"methods":[13],"explore":[14],"various":[15,50],"complicated":[16],"embedding":[17,51,66,71,76,84,102],"spaces":[18,52,85,103],"to":[19,56,113],"assess":[20],"semantic":[22,46,90,156],"similarity":[23],"between":[24],"given":[26],"pair,":[28],"but":[29],"consider":[30],"no/little":[31],"about":[32],"consistency":[34,47,91],"across":[35],"them.":[36],"To":[37],"remedy":[38],"this":[39],"situation,":[40],"we":[41,60,87],"introduce":[42],"idea":[44],"of":[45,80,152,155],"for":[48],"learning":[49,81],"jointly.":[53],"Specifically,":[54],"similar":[55],"previous":[58],"works,":[59],"start":[61],"by":[62],"constructing":[63],"two":[64,83],"different":[65],"spaces,":[67],"namely":[68],"image-grounded":[70],"space":[72],"and":[73,108,128,150],"text-grounded":[75],"space.":[77],"However,":[78],"instead":[79],"these":[82],"separately,":[86],"incorporate":[88],"constraint":[92],"common":[95],"ranking":[96],"objective":[97],"function":[98],"such":[99],"that":[100,133],"both":[101],"can":[104,145],"be":[105],"learned":[106],"simultaneously":[107],"benefit":[109],"from":[110],"each":[111],"other":[112],"gain":[114],"performance":[115],"improvement.":[116],"We":[117],"conduct":[118],"extensive":[119],"experiments":[120],"on":[121,140],"three":[122,142],"benchmark":[123],"datasets,":[124,143],"\\ie":[125],"Flickr8k,":[126],"Flickr30k":[127],"MS":[129],"COCO.":[130],"Results":[131],"show":[132],"our":[134],"model":[135],"outperforms":[136],"state-of-the-art":[138],"models":[139],"all":[141],"which":[144],"well":[146],"demonstrate":[147],"effectiveness":[149],"superiority":[151],"introduction":[154],"consistency.":[157],"Our":[158],"source":[159],"code":[160],"is":[161],"released":[162],"at:":[163],"\\urlhttps://github.com/HuiChen24/SemanticConsistency.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":12}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}