{"id":"https://openalex.org/W4311681660","doi":"https://doi.org/10.1145/3551626.3564945","title":"Self-Attentive CLIP Hashing for Unsupervised Cross-Modal Retrieval","display_name":"Self-Attentive CLIP Hashing for Unsupervised Cross-Modal Retrieval","publication_year":2022,"publication_date":"2022-12-07","ids":{"openalex":"https://openalex.org/W4311681660","doi":"https://doi.org/10.1145/3551626.3564945"},"language":"en","primary_location":{"id":"doi:10.1145/3551626.3564945","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3551626.3564945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM International Conference on Multimedia in Asia","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/A5100511327","display_name":"Heng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Yu","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030160511","display_name":"Shuyan Ding","orcid":"https://orcid.org/0000-0003-2053-1100"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyan Ding","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056439628","display_name":"Lunbo Li","orcid":"https://orcid.org/0000-0003-0834-2075"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lunbo Li","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102715014","display_name":"Jiexin Wu","orcid":"https://orcid.org/0000-0002-2191-0228"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiexin Wu","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":1.0153,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.77488247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9976999759674072,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9936000108718872,"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":0.7890678644180298},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.7303805351257324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6293604373931885},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6289172172546387},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6003382205963135},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5003495216369629},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48677682876586914},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48034632205963135},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.47884082794189453},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.43227097392082214},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3345401883125305},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2299843430519104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7890678644180298},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7303805351257324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6293604373931885},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6289172172546387},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6003382205963135},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5003495216369629},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48677682876586914},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48034632205963135},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47884082794189453},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.43227097392082214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3345401883125305},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2299843430519104},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3551626.3564945","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3551626.3564945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1996219872","https://openalex.org/W2007972815","https://openalex.org/W2086958058","https://openalex.org/W2155803963","https://openalex.org/W2266728343","https://openalex.org/W2512032049","https://openalex.org/W2591669147","https://openalex.org/W2618530766","https://openalex.org/W2748725735","https://openalex.org/W2808243243","https://openalex.org/W2808301810","https://openalex.org/W2889024947","https://openalex.org/W2895249671","https://openalex.org/W2905040928","https://openalex.org/W2963288100","https://openalex.org/W2963495494","https://openalex.org/W3003735286","https://openalex.org/W3035747010","https://openalex.org/W3175740157","https://openalex.org/W3176349206","https://openalex.org/W3186187670","https://openalex.org/W3192973254","https://openalex.org/W3207668481","https://openalex.org/W6754391278"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W2366107444","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366"],"abstract_inverted_index":{"With":[0],"the":[1,14,23,29,57,70,95,112,118,134,144,168,178],"explosive":[2],"growth":[3],"of":[4,146,166,180],"multi-modal":[5],"data":[6],"such":[7],"as":[8],"video,":[9],"images,":[10],"and":[11,44,76,100,149],"text":[12],"on":[13,94,151],"Internet,":[15],"cross-modal":[16,97],"retrieval":[17,87],"has":[18,34,123],"received":[19],"extensive":[20],"attention,":[21],"especially":[22],"deep":[24,32],"hashing":[25,33,98,187],"method.":[26],"Compared":[27],"with":[28,183],"real-value":[30],"method,":[31],"shown":[35,124],"promising":[36],"prospects":[37],"due":[38],"to":[39,61,78,131,142],"its":[40],"low":[41],"memory":[42],"consumption":[43],"high":[45],"searching":[46],"efficiency.":[47],"However,":[48],"most":[49],"existing":[50],"studies":[51],"have":[52],"difficulties":[53],"in":[54,85,127],"effectively":[55],"utilizing":[56],"raw":[58],"image-text":[59],"pairs":[60],"generate":[62],"discriminative":[63],"feature":[64,113],"representations.":[65],"Moreover,":[66],"these":[67],"methods":[68],"ignore":[69],"latent":[71],"relationship":[72],"between":[73],"different":[74,173],"modalities":[75],"fail":[77],"construct":[79,111,158],"a":[80,102,159],"robust":[81],"similarity":[82,162],"matrix,":[83],"resulting":[84],"suboptimal":[86],"performance.":[88],"In":[89],"this":[90,155],"paper,":[91],"we":[92,110,157],"focus":[93,150],"unsupervised":[96,186],"tasks":[99],"propose":[101],"Self":[103],"Attentive":[104],"CLIP":[105,120],"Hashing":[106],"(SACH)":[107],"model.":[108],"Specifically,":[109],"extraction":[114],"network":[115],"by":[116],"employing":[117],"pre-trained":[119],"model,":[121],"which":[122],"excellent":[125],"performance":[126],"zero-shot":[128],"tasks.":[129],"Besides,":[130],"fully":[132],"exploit":[133],"semantic":[135,160,170],"relationships,":[136],"an":[137],"attention":[138],"module":[139],"is":[140],"introduced":[141],"reduce":[143],"disturbance":[145],"redundant":[147],"information":[148],"important":[152],"information.":[153],"On":[154],"basis,":[156],"fusion":[161],"matrix":[163],"that":[164],"capable":[165],"preserving":[167],"original":[169],"relationships":[171],"from":[172],"modalities.":[174],"Extensive":[175],"experiments":[176],"show":[177],"superiority":[179],"SACH":[181],"compared":[182],"recent":[184],"state-of-the-art":[185],"methods.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}