{"id":"https://openalex.org/W4379806236","doi":"https://doi.org/10.1145/3591106.3592242","title":"Learning From Expert: Vision-Language Knowledge Distillation for Unsupervised Cross-Modal Hashing Retrieval","display_name":"Learning From Expert: Vision-Language Knowledge Distillation for Unsupervised Cross-Modal Hashing Retrieval","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379806236","doi":"https://doi.org/10.1145/3591106.3592242"},"language":"en","primary_location":{"id":"doi:10.1145/3591106.3592242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","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/A5006685570","display_name":"Lina Sun","orcid":"https://orcid.org/0000-0002-6190-6039"},"institutions":[{"id":"https://openalex.org/I126924076","display_name":"Chongqing Normal University","ror":"https://ror.org/01dcw5w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I126924076"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lina Sun","raw_affiliation_strings":["School of Computer and Information Science, Chongqing Normal University, China"],"raw_orcid":"https://orcid.org/0000-0002-6190-6039","affiliations":[{"raw_affiliation_string":"School of Computer and Information Science, Chongqing Normal University, China","institution_ids":["https://openalex.org/I126924076"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063575625","display_name":"Yewen Li","orcid":"https://orcid.org/0000-0001-8406-0606"},"institutions":[{"id":"https://openalex.org/I126924076","display_name":"Chongqing Normal University","ror":"https://ror.org/01dcw5w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I126924076"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yewen Li","raw_affiliation_strings":["School of Computer and Information Science, Chongqing Normal University, China"],"raw_orcid":"https://orcid.org/0000-0001-8406-0606","affiliations":[{"raw_affiliation_string":"School of Computer and Information Science, Chongqing Normal University, China","institution_ids":["https://openalex.org/I126924076"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038455283","display_name":"Yumin Dong","orcid":"https://orcid.org/0000-0002-7890-4427"},"institutions":[{"id":"https://openalex.org/I126924076","display_name":"Chongqing Normal University","ror":"https://ror.org/01dcw5w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I126924076"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yumin Dong","raw_affiliation_strings":["School of Computer and Information Science, Chongqing Normal University, China"],"raw_orcid":"https://orcid.org/0000-0002-7890-4427","affiliations":[{"raw_affiliation_string":"School of Computer and Information Science, Chongqing Normal University, China","institution_ids":["https://openalex.org/I126924076"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006685570"],"corresponding_institution_ids":["https://openalex.org/I126924076"],"apc_list":null,"apc_paid":null,"fwci":1.884,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.87805069,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"499","last_page":"507"},"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9925000071525574,"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":0.8348321914672852},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6784709692001343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6078571081161499},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.44222667813301086},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4325319528579712},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4282742738723755},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42419999837875366},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3225816488265991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8348321914672852},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6784709692001343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6078571081161499},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.44222667813301086},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4325319528579712},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4282742738723755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42419999837875366},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3225816488265991},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3591106.3592242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3057605336","display_name":null,"funder_award_id":"No.61772295, 61572270, and 61173056","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":31,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2007972815","https://openalex.org/W2086958058","https://openalex.org/W2155803963","https://openalex.org/W2266728343","https://openalex.org/W2512032049","https://openalex.org/W2765440071","https://openalex.org/W2949588459","https://openalex.org/W2963187862","https://openalex.org/W2982242214","https://openalex.org/W2982905682","https://openalex.org/W3033587904","https://openalex.org/W3033799362","https://openalex.org/W3034890701","https://openalex.org/W3035747010","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3093291618","https://openalex.org/W3122091215","https://openalex.org/W3135367836","https://openalex.org/W3135808071","https://openalex.org/W3155230099","https://openalex.org/W3170224286","https://openalex.org/W3175740157","https://openalex.org/W3176445421","https://openalex.org/W3197447668","https://openalex.org/W3207668481","https://openalex.org/W4285288078","https://openalex.org/W4295736364","https://openalex.org/W4304014690","https://openalex.org/W4306317671"],"related_works":["https://openalex.org/W3196155444","https://openalex.org/W3209574120","https://openalex.org/W4386462264","https://openalex.org/W4285260836","https://openalex.org/W3046775127","https://openalex.org/W3123344745","https://openalex.org/W4367692580","https://openalex.org/W3208099188","https://openalex.org/W4306321456","https://openalex.org/W3007915134"],"abstract_inverted_index":{"Unsupervised":[0,100],"cross-modal":[1,91,246],"hashing":[2,92,159,247],"(UCMH)":[3],"has":[4],"attracted":[5],"increasing":[6],"research":[7],"due":[8,33],"to":[9,34,66,74,112,124,141,145,188,206,211,243],"its":[10],"efficient":[11,220],"retrieval":[12,93,230,240],"performance":[13,241],"and":[14,44,118,216,223],"label":[15],"irrelevance.":[16],"However,":[17],"existing":[18,25,57,244],"methods":[19,27,58],"have":[20,59],"some":[21],"bottlenecks:":[22],"Firstly,":[23],"the":[24,35,50,76,107,130,135,138,142,180,185,195,208,235,250,253],"unsupervised":[26,90,158,245],"suffer":[28],"from":[29,174],"inaccurate":[30],"similarity":[31,122,127,181],"measures":[32],"lack":[36],"of":[37,41,53,70,78,137,149,252],"correlation":[38],"between":[39],"features":[40,46,114],"different":[42],"modalities":[43],"simple":[45],"cannot":[47],"fully":[48],"describe":[49],"fine-grained":[51],"relationships":[52],"multi-modal":[54,68,116,150],"data.":[55],"Secondly,":[56],"rarely":[60],"explored":[61],"vision-language":[62,72,108],"knowledge":[63,69,136],"distillation":[64],"schemes":[65],"distil":[67],"these":[71,83],"models":[73],"guide":[75,207],"learning":[77,160],"student":[79,131,143,209],"networks.":[80],"To":[81],"address":[82],"bottlenecks,":[84],"this":[85],"paper":[86],"proposes":[87],"an":[88,147,156],"effective":[89],"method,":[94],"called":[95],"Vision-Language":[96],"Knowledge":[97],"Distillation":[98],"for":[99,129],"Cross-Modal":[101],"Hashing":[102],"Retrieval":[103],"(VLKD).":[104],"VLKD":[105,217],"uses":[106],"pre-training":[109],"(VLP)":[110],"model":[111,140,144,161,187],"encode":[113],"on":[115,179,227],"data,":[117],"then":[119],"constructs":[120],"a":[121,164],"matrix":[123,182],"provide":[125],"soft":[126],"supervision":[128],"model.":[132],"It":[133],"distils":[134],"VLP":[139],"gain":[146],"understanding":[148],"knowledge.":[151],"In":[152],"addition,":[153],"we":[154],"designed":[155],"end-to-end":[157],"that":[162,234],"incorporates":[163],"graph":[165],"convolutional":[166],"auxiliary":[167,170],"network.":[168],"The":[169],"network":[171,197,210],"aggregates":[172],"information":[173],"similar":[175],"data":[176],"nodes":[177],"based":[178],"distilled":[183],"by":[184],"teacher":[186,196],"generate":[189],"more":[190],"consistent":[191],"hash":[192,214],"codes.":[193],"Finally,":[194],"does":[198],"not":[199],"require":[200],"additional":[201],"training,":[202],"it":[203],"only":[204],"needs":[205],"learn":[212],"high-quality":[213],"representation,":[215],"is":[218],"quite":[219],"in":[221],"training":[222],"retrieval.":[224],"Sufficient":[225],"experiments":[226],"three":[228],"multimedia":[229],"benchmark":[231],"datasets":[232],"show":[233],"proposed":[236,254],"method":[237],"achieves":[238],"better":[239],"compared":[242],"methods,":[248],"demonstrating":[249],"effectiveness":[251],"method.":[255]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}