{"id":"https://openalex.org/W4392678259","doi":"https://doi.org/10.1609/aaai.v38i16.29789","title":"Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrieval","display_name":"Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrieval","publication_year":2024,"publication_date":"2024-03-24","ids":{"openalex":"https://openalex.org/W4392678259","doi":"https://doi.org/10.1609/aaai.v38i16.29789"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v38i16.29789","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i16.29789","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/29789/31364","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/29789/31364","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031578713","display_name":"Hailang Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailang Huang","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059807664","display_name":"Zhijie Nie","orcid":"https://orcid.org/0000-0003-2171-3416"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijie Nie","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042387346","display_name":"Ziqiao Wang","orcid":"https://orcid.org/0000-0003-3383-8670"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ziqiao Wang","raw_affiliation_strings":["University of Ottawa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Ottawa","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008140023","display_name":"Ziyu Shang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyu Shang","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.9916,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.98659288,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"38","issue":"16","first_page":"18298","last_page":"18306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9959999918937683,"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/T11714","display_name":"Multimodal Machine Learning Applications","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"}}],"keywords":[{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.8242526054382324},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5727453827857971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44345709681510925},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41991159319877625},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38968533277511597},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3793972432613373},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.1502954363822937}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.8242526054382324},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5727453827857971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44345709681510925},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41991159319877625},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38968533277511597},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3793972432613373},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.1502954363822937},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1609/aaai.v38i16.29789","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i16.29789","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/29789/31364","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2403.05261","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.05261","pdf_url":"https://arxiv.org/pdf/2403.05261","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ojs.aaai.org:article/29789","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/29789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v38i16.29789","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i16.29789","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/29789/31364","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392678259.pdf"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2126400076","https://openalex.org/W2176040302","https://openalex.org/W2185175083","https://openalex.org/W2251869843","https://openalex.org/W2462305634","https://openalex.org/W2471768434","https://openalex.org/W2987283559","https://openalex.org/W3005680577","https://openalex.org/W3016473712","https://openalex.org/W3106780750","https://openalex.org/W3118694826","https://openalex.org/W3126337491","https://openalex.org/W3184735396","https://openalex.org/W4210894218","https://openalex.org/W4221167445","https://openalex.org/W4223592369","https://openalex.org/W4226182655","https://openalex.org/W4296151206","https://openalex.org/W4312761738","https://openalex.org/W4360897523","https://openalex.org/W4365456772","https://openalex.org/W6600609147","https://openalex.org/W6639102338","https://openalex.org/W6682338420","https://openalex.org/W6691695795","https://openalex.org/W6749537441","https://openalex.org/W6788213132"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Current":[0],"image-text":[1,36,70,114,126,142,160],"retrieval":[2,71,115,127,143,157,161],"methods":[3],"have":[4],"demonstrated":[5],"impressive":[6],"performance":[7,140,158],"in":[8],"recent":[9],"years.":[10],"However,":[11],"they":[12],"still":[13],"face":[14],"two":[15,76],"problems:":[16],"the":[17,23,33,57,69,139,155],"inter-modal":[18],"matching":[19],"missing":[20],"problem":[21],"and":[22,49,83,92,129,144,171],"intra-modal":[24],"semantic":[25],"loss":[26],"problem.":[27],"These":[28],"problems":[29],"can":[30,108,136,152,174],"significantly":[31],"affect":[32],"accuracy":[34],"of":[35,59,141,159],"retrieval.":[37,168],"To":[38],"address":[39],"these":[40],"challenges,":[41],"we":[42,74,131],"propose":[43],"a":[44],"novel":[45],"method":[46,55,100,135,151],"called":[47],"Cross-modal":[48,79],"Uni-modal":[50,84],"Soft-label":[51,80,85],"Alignment":[52,81,86],"(CUSA).":[53],"Our":[54,99],"leverages":[56],"power":[58],"uni-modal":[60,97,156],"pre-trained":[61],"models":[62,116,128],"to":[63,88,103,112,165],"provide":[64],"soft-label":[65],"supervision":[66],"signals":[67],"for":[68],"model.":[72],"Additionally,":[73],"introduce":[75],"alignment":[77],"techniques,":[78],"(CSA)":[82],"(USA),":[87],"overcome":[89],"false":[90],"negatives":[91],"enhance":[93],"similarity":[94],"recognition":[95],"between":[96],"samples.":[98],"is":[101],"designed":[102],"be":[104,109,175],"plug-and-play,":[105],"meaning":[106],"it":[107,164],"easily":[110],"applied":[111],"existing":[113],"without":[117],"changing":[118],"their":[119],"original":[120],"architectures.":[121],"Extensive":[122],"experiments":[123],"on":[124],"various":[125],"datasets,":[130],"demonstrate":[132],"that":[133],"our":[134,150],"consistently":[137],"improve":[138],"achieve":[145,166],"new":[146],"state-of-the-art":[147],"results.":[148],"Furthermore,":[149],"also":[153],"boost":[154],"models,":[162],"enabling":[163],"universal":[167],"The":[169],"code":[170],"supplementary":[172],"files":[173],"found":[176],"at":[177],"https://github.com/lerogo/aaai24_itr_cusa.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}