{"id":"https://openalex.org/W4382657968","doi":"https://doi.org/10.1109/tmm.2023.3289753","title":"Commonsense-Guided Semantic and Relational Consistencies for Image-Text Retrieval","display_name":"Commonsense-Guided Semantic and Relational Consistencies for Image-Text Retrieval","publication_year":2023,"publication_date":"2023-06-30","ids":{"openalex":"https://openalex.org/W4382657968","doi":"https://doi.org/10.1109/tmm.2023.3289753"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3289753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3289753","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-article"},"type":"article","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/A5100339851","display_name":"Wenhui Li","orcid":"https://orcid.org/0000-0001-9609-6120"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhui Li","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-9609-6120","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101972555","display_name":"Song Soo Yang","orcid":"https://orcid.org/0000-0002-8238-8226"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Yang","raw_affiliation_strings":["School of Microelectronics, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-8238-8226","affiliations":[{"raw_affiliation_string":"School of Microelectronics, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429894","display_name":"Qiang Li","orcid":"https://orcid.org/0000-0001-7129-1456"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Li","raw_affiliation_strings":["School of Microelectronics, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-7129-1456","affiliations":[{"raw_affiliation_string":"School of Microelectronics, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024121467","display_name":"Xuanya Li","orcid":"https://orcid.org/0000-0002-2227-207X"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanya Li","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2227-207X","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111001191","display_name":"An-An Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"An-An Liu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China","Institute of Artificial Intelligence, Hefei Comprehensive National Science Center and the Key Laboratory of Electromagnetic Space Information, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5755-9145","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center and the Key Laboratory of Electromagnetic Space Information, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7572,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.85446207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"1867","last_page":"1880"},"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":0.9961000084877014,"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":0.993399977684021,"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/computer-science","display_name":"Computer science","score":0.7311946749687195},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6049519777297974},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5758528709411621},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5371348261833191},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5071694850921631},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.487442284822464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46931883692741394},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.45105448365211487},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.4487069845199585},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42775338888168335},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.2626175880432129},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08621573448181152}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7311946749687195},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6049519777297974},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5758528709411621},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5371348261833191},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5071694850921631},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.487442284822464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46931883692741394},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.45105448365211487},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.4487069845199585},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42775338888168335},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2626175880432129},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08621573448181152},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3289753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3289753","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1611867576","display_name":null,"funder_award_id":"2022M712369","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G173205433","display_name":null,"funder_award_id":"U21B2024","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G70510124","display_name":null,"funder_award_id":"62202327","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7458595415","display_name":"\u9762\u5411\u590d\u6742\u573a\u666f\u89c6\u9891\u7684\u89c6\u89c9\u5173\u7cfb\u68c0\u6d4b\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62072232","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320318547","display_name":"Baidu","ror":"https://ror.org/03vs3wt56"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W64813323","https://openalex.org/W639708223","https://openalex.org/W1527575280","https://openalex.org/W1538241161","https://openalex.org/W1861492603","https://openalex.org/W2064675550","https://openalex.org/W2250539671","https://openalex.org/W2506483933","https://openalex.org/W2546696630","https://openalex.org/W2568262903","https://openalex.org/W2581887665","https://openalex.org/W2795389793","https://openalex.org/W2807873315","https://openalex.org/W2890531016","https://openalex.org/W2894786240","https://openalex.org/W2907492528","https://openalex.org/W2950096400","https://openalex.org/W2962964995","https://openalex.org/W2963052338","https://openalex.org/W2963389687","https://openalex.org/W2963467339","https://openalex.org/W2963536419","https://openalex.org/W2964120214","https://openalex.org/W2964727037","https://openalex.org/W2965848243","https://openalex.org/W2995688498","https://openalex.org/W3004349648","https://openalex.org/W3010277541","https://openalex.org/W3034305926","https://openalex.org/W3035160838","https://openalex.org/W3035454331","https://openalex.org/W3035497460","https://openalex.org/W3035552787","https://openalex.org/W3035605030","https://openalex.org/W3092820619","https://openalex.org/W3092962760","https://openalex.org/W3110042533","https://openalex.org/W3118694826","https://openalex.org/W3133431537","https://openalex.org/W3155230099","https://openalex.org/W3175095612","https://openalex.org/W3182937942","https://openalex.org/W3190055600","https://openalex.org/W3207608362","https://openalex.org/W3214042654","https://openalex.org/W4206314411","https://openalex.org/W4221155360","https://openalex.org/W4221166573","https://openalex.org/W4285118104","https://openalex.org/W4312522167","https://openalex.org/W6631516269","https://openalex.org/W6747225742","https://openalex.org/W6771672396","https://openalex.org/W6810958298"],"related_works":["https://openalex.org/W3035583586","https://openalex.org/W3165136392","https://openalex.org/W2963219906","https://openalex.org/W2221077171","https://openalex.org/W2950339735","https://openalex.org/W2963520511","https://openalex.org/W2971998405","https://openalex.org/W2901964648","https://openalex.org/W3152979241","https://openalex.org/W4323929292"],"abstract_inverted_index":{"Image-text":[0],"retrieval,":[1],"as":[2],"a":[3,52],"fundamental":[4],"task":[5,24],"in":[6,132],"the":[7,13,28,79,85,89,92,97,115,125,130,139,176,192],"cross-modal":[8,34,86,133,143],"field,":[9],"aims":[10],"to":[11,83,113,151,165],"explore":[12,110],"relationship":[14],"between":[15,33,104,179],"visual":[16,119],"and":[17,30,62,81,94,120,123,169],"textual":[18,121],"modalities.":[19,106],"Recent":[20],"methods":[21],"address":[22],"this":[23,48],"only":[25],"by":[26,128,174],"learning":[27],"conceptual":[29],"syntactical":[31],"correspondences":[32,38],"fragments,":[35],"but":[36],"these":[37],"inevitably":[39],"contain":[40],"noise":[41],"without":[42],"considering":[43],"external":[44,159],"knowledge.":[45],"To":[46],"solve":[47],"issue,":[49],"we":[50,108,137,157],"propose":[51],"novel":[53],"<bold":[54,58,63,67],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[55,59,64,68],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">C</b>":[56,69],"ommonsense-Guided":[57],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">S</b>":[60],"emantic":[61],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">R</b>":[65],"elational":[66],"onsistencies":[70],"(CSRC)":[71],"for":[72,118,142],"image-text":[73,99,188],"retrieval":[74,189],"that":[75,91],"can":[76],"simultaneously":[77],"expand":[78,114],"semantics":[80,93],"relations":[82,95,141],"reduce":[84],"differences":[87,131,178],"under":[88],"assumption":[90],"of":[96,194],"true":[98],"pair":[100],"should":[101],"be":[102],"consistent":[103],"two":[105,186],"Specifically,":[107],"first":[109],"commonsense":[111,160],"knowledge":[112,161],"specific":[116],"concepts":[117],"graphs":[122],"optimize":[124,171],"semantic":[126,134,147],"consistency":[127,173],"minimizing":[129],"importance.":[135],"Then,":[136],"extend":[138],"same":[140],"concept":[144,167],"pairs":[145],"with":[146,162],"consistency,":[148],"which":[149],"serves":[150],"implement":[152],"relational":[153,172],"consistency.":[154],"After":[155],"that,":[156],"combine":[158],"internal":[163],"correlation":[164],"enhance":[166],"representation":[168],"further":[170],"regularizing":[175],"importance":[177],"association-enhanced":[180],"concepts.":[181],"Extensive":[182],"experimental":[183],"results":[184],"on":[185],"popular":[187],"datasets":[190],"demonstrate":[191],"effectiveness":[193],"our":[195],"proposed":[196],"method.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}