{"id":"https://openalex.org/W4392904090","doi":"https://doi.org/10.1109/icassp48485.2024.10447444","title":"Multi-Level Contrastive Learning For Hybrid Cross-Modal Retrieval","display_name":"Multi-Level Contrastive Learning For Hybrid Cross-Modal Retrieval","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904090","doi":"https://doi.org/10.1109/icassp48485.2024.10447444"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5039958973","display_name":"Yiming Zhao","orcid":"https://orcid.org/0000-0001-9930-8635"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiming Zhao","raw_affiliation_strings":["Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030033393","display_name":"Haoyu Lu","orcid":"https://orcid.org/0000-0003-2620-6296"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Lu","raw_affiliation_strings":["Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088857350","display_name":"Shiqi Zhao","orcid":"https://orcid.org/0009-0006-2508-7108"},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiqi Zhao","raw_affiliation_strings":["China Unicom Research Institute,Beijing,China","China Unicom Research Institute, Beijing, China"],"affiliations":[{"raw_affiliation_string":"China Unicom Research Institute,Beijing,China","institution_ids":["https://openalex.org/I6507939"]},{"raw_affiliation_string":"China Unicom Research Institute, Beijing, China","institution_ids":["https://openalex.org/I6507939"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100769821","display_name":"Haoran Wu","orcid":"https://orcid.org/0000-0001-5822-8698"},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Wu","raw_affiliation_strings":["China Unicom Research Institute,Beijing,China","China Unicom Research Institute, Beijing, China"],"affiliations":[{"raw_affiliation_string":"China Unicom Research Institute,Beijing,China","institution_ids":["https://openalex.org/I6507939"]},{"raw_affiliation_string":"China Unicom Research Institute, Beijing, China","institution_ids":["https://openalex.org/I6507939"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103244144","display_name":"Zhiwu Lu","orcid":"https://orcid.org/0000-0001-6429-7956"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwu Lu","raw_affiliation_strings":["Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039958973"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.7873,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70146335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6390","last_page":"6394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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":0.9993000030517578,"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":0.9901999831199646,"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":0.8450461030006409},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6636263132095337},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6311969757080078},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5398373603820801},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49387985467910767},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47518956661224365},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.46606212854385376},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.45877254009246826},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42209726572036743},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.29732707142829895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8450461030006409},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6636263132095337},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6311969757080078},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5398373603820801},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49387985467910767},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47518956661224365},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.46606212854385376},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.45877254009246826},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42209726572036743},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29732707142829895},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2194775991","https://openalex.org/W2412393473","https://openalex.org/W2760103357","https://openalex.org/W2798503981","https://openalex.org/W2842511635","https://openalex.org/W2905544595","https://openalex.org/W2964015378","https://openalex.org/W3013548136","https://openalex.org/W3026458074","https://openalex.org/W3034585290","https://openalex.org/W3038703236","https://openalex.org/W3092962760","https://openalex.org/W3119510203","https://openalex.org/W3150955418","https://openalex.org/W3172514680","https://openalex.org/W3175684172","https://openalex.org/W3176909828","https://openalex.org/W3203247393","https://openalex.org/W3205173298","https://openalex.org/W3206128852","https://openalex.org/W4206811189","https://openalex.org/W4226371180","https://openalex.org/W4292828970","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6715144786","https://openalex.org/W6726873649","https://openalex.org/W6751039726","https://openalex.org/W6775439340","https://openalex.org/W6780783783","https://openalex.org/W6791353385","https://openalex.org/W6793664725","https://openalex.org/W6807421888","https://openalex.org/W6810496820","https://openalex.org/W6810517887"],"related_works":["https://openalex.org/W2364155688","https://openalex.org/W2046522763","https://openalex.org/W2366916257","https://openalex.org/W2375847997","https://openalex.org/W2072836406","https://openalex.org/W2391772185","https://openalex.org/W2061641547","https://openalex.org/W4386420450","https://openalex.org/W2355099127","https://openalex.org/W2361892564"],"abstract_inverted_index":{"Hybrid":[0],"image":[1,26,33],"retrieval":[2,134],"is":[3],"a":[4,8,24,28,35,63,76],"significant":[5],"task":[6],"for":[7,19,69],"wide":[9],"range":[10],"of":[11,23,99,105],"applications.":[12],"In":[13],"this":[14],"scenario,":[15],"the":[16,45,49,52,71,96,100,106,127,131],"hybrid":[17,58,72,132],"query":[18,73],"searching":[20],"images":[21],"consists":[22],"reference":[25,32,53],"and":[27,39,118],"text":[29,46],"modifier.":[30],"The":[31],"provides":[34],"vital":[36],"visual":[37],"context":[38],"displays":[40],"some":[41],"semantic":[42,85,97],"details,":[43],"while":[44],"modifier":[47],"specifies":[48],"modifications":[50],"to":[51,94],"image.":[54],"To":[55],"address":[56],"such":[57],"cross-modal":[59,80,133],"retrieval,":[60],"we":[61,88],"propose":[62],"multi-level":[64,84],"contrastive":[65,81,92],"learning":[66,82,93],"(MLCL)":[67],"method":[68],"combining":[70],"features":[74,101],"into":[75],"fused":[77],"feature":[78],"by":[79],"with":[83],"alignment.":[86],"Meanwhile,":[87],"additionally":[89],"consider":[90],"self-supervised":[91],"enhance":[95],"correlation":[98],"at":[102],"different":[103],"levels":[104],"combiner":[107],"network.":[108],"Extensive":[109],"results":[110],"on":[111],"three":[112],"public":[113],"datasets":[114],"(i.e.,":[115],"FashionIQ,":[116],"Shoes,":[117],"CIRR)":[119],"demonstrate":[120],"that":[121],"our":[122],"proposed":[123],"MLCL":[124],"significantly":[125],"outperforms":[126],"state-of-the-art":[128],"methods":[129],"under":[130],"setting.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}