{"id":"https://openalex.org/W4403577365","doi":"https://doi.org/10.1145/3627673.3679619","title":"Image-text Retrieval with Main Semantics Consistency","display_name":"Image-text Retrieval with Main Semantics Consistency","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403577365","doi":"https://doi.org/10.1145/3627673.3679619"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679619","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","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/A5110379120","display_name":"Yi Xie","orcid":"https://orcid.org/0009-0009-6048-7491"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Xie","raw_affiliation_strings":["School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-6048-7491","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012931252","display_name":"Yangtao Wang","orcid":"https://orcid.org/0000-0003-4605-9270"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangtao Wang","raw_affiliation_strings":["School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4605-9270","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050542870","display_name":"Yanzhao Xie","orcid":"https://orcid.org/0000-0002-9274-2807"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanzhao Xie","raw_affiliation_strings":["School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9274-2807","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080281882","display_name":"Xin Tan","orcid":"https://orcid.org/0000-0001-9346-1196"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Tan","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9346-1196","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338386","display_name":"Jingjing Li","orcid":"https://orcid.org/0000-0002-5504-2529"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Li","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5504-2529","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100723331","display_name":"Xiaocui Li","orcid":"https://orcid.org/0000-0002-5971-2331"},"institutions":[{"id":"https://openalex.org/I49934816","display_name":"Hunan University of Technology","ror":"https://ror.org/04j3vr751","country_code":"CN","type":"education","lineage":["https://openalex.org/I49934816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaocui Li","raw_affiliation_strings":["Hunan University of Technology and Business, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-5971-2331","affiliations":[{"raw_affiliation_string":"Hunan University of Technology and Business, Changsha, China","institution_ids":["https://openalex.org/I49934816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052138365","display_name":"Weilong Peng","orcid":"https://orcid.org/0000-0001-5820-889X"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weilong Peng","raw_affiliation_strings":["School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5820-889X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067384850","display_name":"Maobin Tang","orcid":"https://orcid.org/0009-0005-5448-4172"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maobin Tang","raw_affiliation_strings":["School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-5448-4172","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073389511","display_name":"Meie Fang","orcid":"https://orcid.org/0000-0003-4292-8889"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meie Fang","raw_affiliation_strings":["School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4292-8889","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2629","last_page":"2638"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9983999729156494,"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":0.8205775022506714},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.725830078125},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6468402147293091},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6424909830093384},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5669682025909424},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.486198365688324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4581313729286194},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3474164605140686},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19131439924240112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8205775022506714},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.725830078125},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6468402147293091},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6424909830093384},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5669682025909424},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.486198365688324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4581313729286194},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3474164605140686},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19131439924240112}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679619","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1956340063","https://openalex.org/W2001832483","https://openalex.org/W2962964995","https://openalex.org/W2982078236","https://openalex.org/W2988823324","https://openalex.org/W2994818707","https://openalex.org/W3010277541","https://openalex.org/W3035454331","https://openalex.org/W3035588244","https://openalex.org/W3109485382","https://openalex.org/W3110042533","https://openalex.org/W3118694826","https://openalex.org/W3131251978","https://openalex.org/W3155230099","https://openalex.org/W3175888430","https://openalex.org/W3183778205","https://openalex.org/W3189718596","https://openalex.org/W3190055600","https://openalex.org/W3206477365","https://openalex.org/W3212847756","https://openalex.org/W3217228024","https://openalex.org/W4206314411","https://openalex.org/W4225166070","https://openalex.org/W4282942960","https://openalex.org/W4285118104","https://openalex.org/W4292092982","https://openalex.org/W4293519407","https://openalex.org/W4301409532","https://openalex.org/W4304084163","https://openalex.org/W4306317000","https://openalex.org/W4312055654","https://openalex.org/W4312477797","https://openalex.org/W4312761738","https://openalex.org/W4312846625","https://openalex.org/W4321608135","https://openalex.org/W4323797084","https://openalex.org/W4366851068","https://openalex.org/W4379382581","https://openalex.org/W4381327576","https://openalex.org/W4386160421","https://openalex.org/W4386388510"],"related_works":["https://openalex.org/W1603736412","https://openalex.org/W4304185162","https://openalex.org/W2061685118","https://openalex.org/W2393699422","https://openalex.org/W4323929292","https://openalex.org/W2168037874","https://openalex.org/W2135728080","https://openalex.org/W2379546782","https://openalex.org/W2534443799","https://openalex.org/W2148968119"],"abstract_inverted_index":{"Image-text":[0],"retrieval":[1,132,254,273],"(ITR)":[2],"has":[3,27],"been":[4,28],"one":[5],"of":[6,87,138,165,176,214,239,266,278],"the":[7,58,72,76,82,114,123,127,131,145,149,156,160,185,189,203,211,236,250,263,270],"primary":[8],"tasks":[9],"in":[10,63,71,135],"cross-modal":[11],"retrieval,":[12],"serving":[13],"as":[14],"a":[15,47,97,102,163,170],"crucial":[16],"bridge":[17],"between":[18,37,53,151,162,191],"computer":[19],"vision":[20],"and":[21,34,39,44,173,183,194,207,260],"natural":[22],"language":[23],"processing.":[24],"Significant":[25],"progress":[26],"made":[29],"to":[30,50,112,122,169,180,242],"achieve":[31],"global":[32],"alignment":[33,36],"local":[35],"images":[38,43,118,217],"texts":[40,45,166,177],"by":[41],"mapping":[42],"into":[46],"common":[48],"space":[49],"establish":[51],"correspondences":[52],"these":[54],"two":[55,153,216],"modalities.":[56],"However,":[57],"rich":[59],"semantic":[60],"content":[61],"contained":[62],"each":[64,136,192,195,240],"image":[65,193,241],"may":[66],"bring":[67],"false":[68],"matches,":[69],"resulting":[70],"matched":[73,244],"text":[74,224],"ignoring":[75],"main":[77,212,237],"semantics":[78,86,213,238],"but":[79],"focusing":[80],"on":[81,258],"secondary":[83],"or":[84],"other":[85],"this":[88,92,94,231,279],"image.":[89],"To":[90],"address":[91],"issue,":[93],"paper":[95],"proposes":[96],"semantically":[98,115,228,251],"optimized":[99],"approach":[100],"with":[101,245,269],"novel":[103],"Main":[104],"Semantics":[105],"Consistency":[106],"(MSC)":[107],"loss":[108],"function,":[109],"which":[110],"aims":[111],"rank":[113],"most":[116,252],"similar":[117],"(or":[119],"texts)":[120],"corresponding":[121,247],"given":[124],"query":[125],"at":[126,283],"top":[128],"position":[129],"during":[130],"process.":[133],"First,":[134],"batch":[137],"image-text":[139,186,272],"pairs,":[140],"we":[141,233],"separately":[142],"compute":[143],"(i)":[144],"image-image":[146],"similarity,":[147,158,187,209],"i.e.,":[148,159,188],"similarity":[150,161,190],"every":[152,215],"images,":[154],"(ii)":[155],"text-text":[157,208],"group":[164,175],"(that":[167,178],"belong":[168,179],"certain":[171],"image)":[172],"another":[174,181],"image),":[182],"(iii)":[184],"text.":[196],"Afterward,":[197],"our":[198],"proposed":[199],"MSC":[200,267],"effectively":[201],"aligns":[202],"above":[204],"image-image,":[205],"image-text,":[206],"since":[210],"will":[218],"be":[219,243],"highly":[220,227],"close":[221],"if":[222],"their":[223],"descriptions":[225],"remain":[226],"consistent.":[229],"By":[230],"means,":[232],"can":[234],"capture":[235],"its":[246],"texts,":[248],"prioritizing":[249],"related":[253],"results.":[255],"Extensive":[256],"experiments":[257],"MSCOCO":[259],"FLICKR30K":[261],"verify":[262],"superior":[264],"performance":[265],"compared":[268],"SOTA":[271],"methods.":[274],"The":[275],"source":[276],"code":[277],"project":[280],"is":[281],"released":[282],"GitHub:":[284],"https://github.com/xyi007/MSC.":[285]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}