{"id":"https://openalex.org/W4412396232","doi":"https://doi.org/10.1145/3726302.3729899","title":"AV-NAS: Audio-Visual Multi-Level Semantic Neural Architecture Search for Video Hashing","display_name":"AV-NAS: Audio-Visual Multi-Level Semantic Neural Architecture Search for Video Hashing","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412396232","doi":"https://doi.org/10.1145/3726302.3729899"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3729899","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729899","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729899","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729899","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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"],"raw_orcid":"https://orcid.org/0000-0002-1348-9218","affiliations":[{"raw_affiliation_string":"School of Computer Science, BUPT, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099295756","display_name":"Yuxiang Zhou","orcid":"https://orcid.org/0009-0002-4124-4151"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxiang Zhou","raw_affiliation_strings":["School of Computer Science, BUPT, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-4124-4151","affiliations":[{"raw_affiliation_string":"School of Computer Science, BUPT, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062792648","display_name":"Hailiang Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hailiang Dong","raw_affiliation_strings":["School of Computer Science, BUPT, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-6177-8440","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/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":"Rui Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1373-6108","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016399094","display_name":"Zhouchen Lin","orcid":"https://orcid.org/0000-0003-1493-7569"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhouchen Lin","raw_affiliation_strings":["School of Intelligence Science and Technology, Peking University, Beijing, China, State Key Lab of General AI &amp; Institute for AI, Peking University, Beijing, China, and Pazhou Laboratory, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1493-7569","affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Peking University, Beijing, China, State Key Lab of General AI &amp; Institute for AI, Peking University, Beijing, China, and Pazhou Laboratory, Guangzhou, China","institution_ids":["https://openalex.org/I20231570"]}]},{"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/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dell Zhang","raw_affiliation_strings":["Institute for Artificial Intelligence, China TeleAI, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8774-3725","affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, China TeleAI, Shanghai, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12641057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"895","last_page":"905"},"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/T11439","display_name":"Video Analysis and Summarization","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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9977999925613403,"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":0.8713880777359009},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5610252618789673},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5019354820251465},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4213172197341919},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3558441996574402},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3528648614883423},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34404754638671875},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.27013373374938965},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10206595063209534}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8713880777359009},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5610252618789673},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5019354820251465},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4213172197341919},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3558441996574402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3528648614883423},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34404754638671875},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.27013373374938965},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10206595063209534},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3729899","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729899","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729899","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3729899","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729899","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729899","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1678053090","display_name":null,"funder_award_id":"62276004","funder_id":"https://openalex.org/F4320324787","funder_display_name":"Peking University"},{"id":"https://openalex.org/G2515039924","display_name":null,"funder_award_id":"62276004, 62372054","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G3896424926","display_name":null,"funder_award_id":"62276004","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412396232.pdf","grobid_xml":"https://content.openalex.org/works/W4412396232.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1777628566","https://openalex.org/W1910300841","https://openalex.org/W1927052826","https://openalex.org/W2084363474","https://openalex.org/W2510911086","https://openalex.org/W2527195341","https://openalex.org/W2527357643","https://openalex.org/W2563615176","https://openalex.org/W2766209167","https://openalex.org/W2785366763","https://openalex.org/W2885311373","https://openalex.org/W2900790473","https://openalex.org/W2932077855","https://openalex.org/W2997536517","https://openalex.org/W2998036008","https://openalex.org/W2999412666","https://openalex.org/W3004085219","https://openalex.org/W3028385587","https://openalex.org/W3034239448","https://openalex.org/W3096533519","https://openalex.org/W3135367836","https://openalex.org/W3156192120","https://openalex.org/W3159735885","https://openalex.org/W3166396011","https://openalex.org/W3167266074","https://openalex.org/W3202742610","https://openalex.org/W3204801262","https://openalex.org/W4205817612","https://openalex.org/W4300687381","https://openalex.org/W4304015043","https://openalex.org/W4310248881","https://openalex.org/W4312810897","https://openalex.org/W4372347247","https://openalex.org/W4382240197","https://openalex.org/W4385199245","https://openalex.org/W4385245566","https://openalex.org/W4385482738","https://openalex.org/W4385822491","https://openalex.org/W4386076017","https://openalex.org/W4388035420","https://openalex.org/W4388191690","https://openalex.org/W4388666357","https://openalex.org/W4391274923","https://openalex.org/W4392061654","https://openalex.org/W4392205891","https://openalex.org/W4403791668","https://openalex.org/W6600238479","https://openalex.org/W6739901393","https://openalex.org/W6753278433"],"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/W2038503502"],"abstract_inverted_index":{"Existing":[0],"video":[1,6,68,140],"hashing":[2,69],"techniques":[3],"for":[4],"large-scale":[5,139],"retrieval":[7,17],"often":[8],"overlook":[9],"inherent":[10],"audio":[11,23],"signals,":[12,24,83],"which":[13,128],"can":[14,145],"potentially":[15],"compromise":[16],"performance.":[18],"Incorporating":[19],"both":[20],"visual":[21],"and":[22,98,109,152],"however,":[25],"complicates":[26],"neural":[27,37],"architecture":[28,79],"design,":[29],"rendering":[30],"the":[31,66,116,163],"manual":[32],"crafting":[33],"of":[34,115],"joint":[35],"audio-visual":[36,60,82],"network":[38,61,91],"models":[39],"challenging.":[40],"To":[41],"address":[42],"this":[43],"issue,":[44],"we":[45,129],"propose":[46],"AV-NAS,":[47],"a":[48,58,75,85,112,123],"method":[49],"that":[50,143],"leverages":[51],"data-driven":[52],"Neural":[53],"Architecture":[54],"Search":[55],"(NAS)":[56],"within":[57],"tailored":[59],"space":[62,88],"to":[63,154],"automatically":[64],"discover":[65,146],"optimal":[67],"network.":[70],"Our":[71,136],"approach":[72],"offers:":[73],"(1)":[74],"versatile":[76],"multi-level":[77],"semantic":[78],"based":[80],"on":[81,138],"defining":[84],"mixed":[86],"search":[87,118],"encompassing":[89],"diverse":[90],"modules":[92],"such":[93],"as":[94,100,102],"MLP,":[95],"CNN,":[96],"Transformer,":[97],"Mamba,":[99],"well":[101],"operations":[103],"like":[104],"Add,":[105],"Hadamard,":[106],"SiLU,":[107],"LayerNorm,":[108],"Skip;":[110],"(2)":[111],"differentiable":[113,125],"relaxation":[114],"combinatorial":[117],"problem,":[119],"converting":[120],"it":[121],"into":[122],"unified":[124],"optimization":[126],"problem":[127],"tackle":[130],"through":[131],"our":[132],"''coarse":[133],"search-pruning-finetuning''":[134],"strategy.":[135],"experiments":[137],"datasets":[141],"show":[142],"AV-NAS":[144],"architectures":[147],"distinct":[148],"from":[149],"expert":[150],"designs":[151],"lead":[153],"substantial":[155],"performance":[156],"improvements":[157],"over":[158],"current":[159],"state-of-the-art":[160],"methods":[161],"including":[162],"recently":[164],"emerged":[165],"AVHash.":[166]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
