{"id":"https://openalex.org/W4402981994","doi":"https://doi.org/10.1109/icme57554.2024.10687993","title":"AsCL: An Asymmetry-sensitive Contrastive Learning Method for Image-Text Retrieval with Cross-Modal Fusion","display_name":"AsCL: An Asymmetry-sensitive Contrastive Learning Method for Image-Text Retrieval with Cross-Modal Fusion","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402981994","doi":"https://doi.org/10.1109/icme57554.2024.10687993"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5045374497","display_name":"Ziyu Gong","orcid":"https://orcid.org/0009-0008-0525-3089"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyu Gong","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074496629","display_name":"Chengcheng Mai","orcid":"https://orcid.org/0000-0002-6185-8858"},"institutions":[{"id":"https://openalex.org/I152031979","display_name":"Nanjing Normal University","ror":"https://ror.org/036trcv74","country_code":"CN","type":"education","lineage":["https://openalex.org/I152031979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengcheng Mai","raw_affiliation_strings":["Nanjing Normal University,School of Computer Science and Electronic Information/School of Artifical Intelligence,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing Normal University,School of Computer Science and Electronic Information/School of Artifical Intelligence,Nanjing,China","institution_ids":["https://openalex.org/I152031979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007538828","display_name":"Yihua Huang","orcid":"https://orcid.org/0000-0003-1806-0936"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihua Huang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9918000102043152,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9918000102043152,"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":0.9613000154495239,"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/modal","display_name":"Modal","score":0.7146665453910828},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7072035074234009},{"id":"https://openalex.org/keywords/asymmetry","display_name":"Asymmetry","score":0.6555832624435425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5865640044212341},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5017802715301514},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47732263803482056},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4145240783691406},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.413707971572876},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3682017922401428},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.30902981758117676},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20236912369728088},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1299372911453247},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.11039113998413086}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7146665453910828},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7072035074234009},{"id":"https://openalex.org/C38976095","wikidata":"https://www.wikidata.org/wiki/Q752641","display_name":"Asymmetry","level":2,"score":0.6555832624435425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5865640044212341},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5017802715301514},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47732263803482056},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4145240783691406},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.413707971572876},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3682017922401428},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.30902981758117676},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20236912369728088},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1299372911453247},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.11039113998413086},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2149557440","https://openalex.org/W2962964995","https://openalex.org/W3035454331","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3094172275","https://openalex.org/W3105486918","https://openalex.org/W3155230099","https://openalex.org/W3166304536","https://openalex.org/W3171668871","https://openalex.org/W3175888430","https://openalex.org/W3184784418","https://openalex.org/W3213586699","https://openalex.org/W4313178921","https://openalex.org/W4313181088","https://openalex.org/W4386075908","https://openalex.org/W4390872633"],"related_works":["https://openalex.org/W3149880372","https://openalex.org/W2788731446","https://openalex.org/W2204403038","https://openalex.org/W3152170969","https://openalex.org/W2379054866","https://openalex.org/W2549658594","https://openalex.org/W2095903272","https://openalex.org/W2370195708","https://openalex.org/W1490651872","https://openalex.org/W2139242969"],"abstract_inverted_index":{"The":[0,15],"image-text":[1],"retrieval":[2],"task":[3],"aims":[4],"to":[5,19,65,126],"retrieve":[6],"relevant":[7],"information":[8,68],"from":[9],"a":[10,76,108,122],"given":[11],"image":[12],"or":[13],"text.":[14],"main":[16],"challenge":[17],"is":[18,113],"unify":[20],"multimodal":[21,123],"representation":[22,45,104],"and":[23,33,46,86,101,118,135,140],"distinguish":[24],"fine-grained":[25,53,98],"differences":[26,54],"across":[27,55],"modalities,":[28],"thereby":[29],"finding":[30],"similar":[31],"contents":[32],"filtering":[34],"irrelevant":[35],"contents.":[36],"However,":[37],"existing":[38],"methods":[39],"mainly":[40],"focus":[41],"on":[42,133],"unified":[43,102],"semantic":[44,99,103],"concept":[47,128],"alignment":[48],"for":[49,89],"multi-modalities,":[50],"while":[51],"the":[52,67,138],"modalities":[56],"have":[57],"rarely":[58],"been":[59],"studied":[60],"before,":[61],"making":[62],"it":[63],"difficult":[64],"solve":[66],"asymmetry":[69,91],"problem.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"propose":[75],"novel":[77],"asymmetry-sensitive":[78],"contrastive":[79],"learning":[80],"method.":[81,145],"By":[82],"generating":[83],"corresponding":[84],"positive":[85],"negative":[87],"samples":[88],"different":[90],"types,":[92],"our":[93,143],"method":[94,112],"can":[95],"simultaneously":[96],"ensure":[97],"differentiation":[100],"between":[105],"multi-modalities.":[106],"Additionally,":[107],"hierarchical":[109],"cross-modal":[110],"fusion":[111],"proposed,":[114],"which":[115],"integrates":[116],"global":[117],"local-level":[119],"features":[120],"through":[121],"attention":[124],"mechanism":[125],"achieve":[127],"alignment.":[129],"Extensive":[130],"experiments":[131],"performed":[132],"MSCOCO":[134],"Flickr30K,":[136],"demonstrate":[137],"effectiveness":[139],"superiority":[141],"of":[142],"proposed":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}