{"id":"https://openalex.org/W4403791668","doi":"https://doi.org/10.1145/3664647.3681266","title":"AVHash: Joint Audio-Visual Hashing for Video Retrieval","display_name":"AVHash: Joint Audio-Visual Hashing for Video Retrieval","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791668","doi":"https://doi.org/10.1145/3664647.3681266"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681266","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5099295756","display_name":"Yuxiang Zhou","orcid":"https://orcid.org/0009-0002-4124-4151"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuxiang Zhou","raw_affiliation_strings":["School of Computer Science, BUPT, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, BUPT, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081872044","display_name":"Zhe Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhe Sun","raw_affiliation_strings":["School of Computer Science, BUPT, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, BUPT, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033416142","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0003-1373-6108"},"institutions":[{"id":"https://openalex.org/I4210137558","display_name":"Beijing University of Agriculture","ror":"https://ror.org/03t9adt98","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210137558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Liu","raw_affiliation_strings":["School of Computer Science, BUAA, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, BUAA, Beijing, China","institution_ids":["https://openalex.org/I4210137558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630707","display_name":"Yong Chen","orcid":"https://orcid.org/0000-0002-1348-9218"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Chen","raw_affiliation_strings":["School of Computer Science, BUPT, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, BUPT, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015784640","display_name":"Dell Zhang","orcid":"https://orcid.org/0000-0002-8774-3725"},"institutions":[{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]},{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dell Zhang","raw_affiliation_strings":["TeleAI, China Telecom, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"TeleAI, China Telecom, Shanghai, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5099295756"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7895,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74007872,"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":"2370","last_page":"2378"},"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8234659433364868},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7124234437942505},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5484396815299988},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5013613700866699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4760415554046631},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.45422959327697754},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.41680338978767395},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.382502019405365},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3623775839805603},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.30515071749687195},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12362608313560486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8234659433364868},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7124234437942505},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5484396815299988},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5013613700866699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4760415554046631},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.45422959327697754},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.41680338978767395},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.382502019405365},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3623775839805603},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.30515071749687195},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12362608313560486},{"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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681266","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1726527000","https://openalex.org/W1777628566","https://openalex.org/W1910300841","https://openalex.org/W1927052826","https://openalex.org/W1974647172","https://openalex.org/W2064675550","https://openalex.org/W2112796928","https://openalex.org/W2510911086","https://openalex.org/W2527195341","https://openalex.org/W2527357643","https://openalex.org/W2563615176","https://openalex.org/W2766209167","https://openalex.org/W2900790473","https://openalex.org/W2955743965","https://openalex.org/W2997536517","https://openalex.org/W2999412666","https://openalex.org/W3028385587","https://openalex.org/W3034239448","https://openalex.org/W3128401049","https://openalex.org/W3135367836","https://openalex.org/W3156192120","https://openalex.org/W3159735885","https://openalex.org/W3166396011","https://openalex.org/W3177244733","https://openalex.org/W4283379644","https://openalex.org/W4304015043","https://openalex.org/W4312810897","https://openalex.org/W4382240197","https://openalex.org/W4383503840","https://openalex.org/W4385270399","https://openalex.org/W4386076017","https://openalex.org/W4388035420"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"Video":[0],"hashing":[1,22,50,149,162],"is":[2,94,122],"a":[3,46,80,86,90,125,132],"technique":[4,51],"of":[5,118,174],"encoding":[6],"videos":[7,34],"into":[8,79],"binary":[9,31],"vectors,":[10],"facilitating":[11],"efficient":[12],"video":[13,21,53,114,148,152,161,183],"storage":[14],"and":[15,61,68,72,77],"high-speed":[16],"computation.":[17],"Current":[18],"approaches":[19],"to":[20,28,96,111],"predominantly":[23],"utilize":[24],"sequential":[25],"frame":[26],"images":[27],"produce":[29],"semantic":[30,83,133],"codes.":[32],"However,":[33],"encompass":[35],"not":[36],"only":[37],"visual":[38,62,166],"but":[39],"also":[40],"audio":[41,60,76,175],"signals.":[42,139],"Therefore,":[43],"we":[44],"propose":[45],"tri-level":[47],"Transformer-based":[48],"audio-visual":[49,100,138],"for":[52,137,182],"retrieval,":[54],"named":[55],"AVHash.":[56],"It":[57],"first":[58],"processes":[59],"signals":[63,101,167,176],"separately":[64],"using":[65,85],"pre-trained":[66],"AST":[67],"ViT":[69],"large":[70],"models,":[71],"then":[73],"projects":[74],"temporal":[75],"keyframes":[78],"shared":[81],"latent":[82],"space":[84],"Transformer":[87,108],"encoder.":[88],"Subsequently,":[89],"gated":[91],"attention":[92],"mechanism":[93],"designed":[95],"fuse":[97],"the":[98,103,112,172],"paired":[99],"in":[102,151],"video,":[104],"followed":[105],"by":[106,124],"another":[107],"encoder":[109],"leading":[110],"final":[113],"representation.":[115],"The":[116],"training":[117],"this":[119],"AVHash":[120,144],"model":[121],"directed":[123],"video-based":[126],"contrastive":[127],"loss":[128],"as":[129,131],"well":[130],"alignment":[134],"regularization":[135],"term":[136],"Experimental":[140],"results":[141],"show":[142],"that":[143,159],"significantly":[145],"outperforms":[146],"existing":[147],"methods":[150],"retrieval":[153],"tasks.":[154],"Furthermore,":[155],"ablation":[156],"studies":[157],"reveal":[158],"while":[160],"based":[163],"solely":[164],"on":[165],"achieves":[168],"commendable":[169],"mAP":[170],"scores,":[171],"incorporation":[173],"can":[177],"further":[178],"boost":[179],"its":[180],"performance":[181],"retrieval.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
