{"id":"https://openalex.org/W3161037578","doi":"https://doi.org/10.1109/icassp39728.2021.9413617","title":"Exploring Visual-Audio Composition Alignment Network for Quality Fashion Retrieval in Video","display_name":"Exploring Visual-Audio Composition Alignment Network for Quality Fashion Retrieval in Video","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161037578","doi":"https://doi.org/10.1109/icassp39728.2021.9413617","mag":"3161037578"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5101930309","display_name":"Yanhao Zhang","orcid":"https://orcid.org/0000-0001-8612-989X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yanhao Zhang","raw_affiliation_strings":["Machine Intelligence Technology Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020280128","display_name":"Jianmin Wu","orcid":"https://orcid.org/0000-0002-0999-9194"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianmin Wu","raw_affiliation_strings":["Machine Intelligence Technology Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752678","display_name":"Xiong Xiong","orcid":"https://orcid.org/0000-0002-5992-9733"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiong Xiong","raw_affiliation_strings":["Machine Intelligence Technology Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052878078","display_name":"Dangwei Li","orcid":"https://orcid.org/0000-0001-5252-9174"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dangwei Li","raw_affiliation_strings":["Machine Intelligence Technology Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101500407","display_name":"Chen-Wei Xie","orcid":"https://orcid.org/0000-0003-1124-3422"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenwei Xie","raw_affiliation_strings":["Machine Intelligence Technology Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058744406","display_name":"Yun Zheng","orcid":"https://orcid.org/0000-0002-1612-7191"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Zheng","raw_affiliation_strings":["Machine Intelligence Technology Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667153","display_name":"Pan Pan","orcid":"https://orcid.org/0000-0001-5828-0234"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pan Pan","raw_affiliation_strings":["Machine Intelligence Technology Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110763379","display_name":"Yinghui Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinghui Xu","raw_affiliation_strings":["Machine Intelligence Technology Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101930309"],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":0.0961,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.36099673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9937999844551086,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9937999844551086,"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/T11019","display_name":"Image Enhancement Techniques","score":0.991100013256073,"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":0.9753000140190125,"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":0.8927921652793884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49082860350608826},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4669666588306427},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4195961654186249},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.41491714119911194},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.371478796005249},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34277498722076416},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.321725070476532},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12831565737724304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8927921652793884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49082860350608826},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4669666588306427},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4195961654186249},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.41491714119911194},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.371478796005249},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34277498722076416},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.321725070476532},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12831565737724304},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":24,"referenced_works":["https://openalex.org/W2100142570","https://openalex.org/W2101552841","https://openalex.org/W2463071499","https://openalex.org/W2625758617","https://openalex.org/W2808965910","https://openalex.org/W2896457183","https://openalex.org/W2896591327","https://openalex.org/W2904451048","https://openalex.org/W2905544595","https://openalex.org/W2913841731","https://openalex.org/W2962934715","https://openalex.org/W2962974137","https://openalex.org/W2963216120","https://openalex.org/W2963341956","https://openalex.org/W2963351448","https://openalex.org/W2963559058","https://openalex.org/W2963588253","https://openalex.org/W2964288524","https://openalex.org/W2985498366","https://openalex.org/W2998705539","https://openalex.org/W3034643643","https://openalex.org/W3094277917","https://openalex.org/W3128537296","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W2357523926","https://openalex.org/W2889616422"],"abstract_inverted_index":{"Fashion":[0],"retrieval":[1,79],"in":[2,80,89,143],"video":[3,134],"suffers":[4],"from":[5,31,102],"the":[6,19,28,59,85,137],"issues":[7],"of":[8,15,37,140],"imperfect":[9],"visual":[10,32,104],"representation":[11],"and":[12,95,105,121],"low":[13],"quality":[14,43,77,110,145],"search":[16],"results":[17],"under":[18],"E-commercial":[20],"circumstance.":[21],"Previous":[22],"works":[23],"generally":[24],"focus":[25],"on":[26,132],"searching":[27],"identical":[29],"images":[30],"perspective":[33],"only,":[34],"but":[35],"lack":[36],"leveraging":[38],"multi-modal":[39],"information":[40,56],"for":[41,125],"high":[42],"commodities.":[44],"As":[45],"a":[46,67,109],"cross-domain":[47],"problem,":[48],"instructional":[49],"or":[50],"exhibiting":[51],"audio":[52,106],"reveals":[53],"rich":[54],"semantic":[55,100],"to":[57,74,92],"facilite":[58],"video-to-shop":[60],"task.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,83],"present":[66],"novel":[68],"Visual-Audio":[69],"Composition":[70],"Alignment":[71],"Network":[72],"(VACANet)":[73],"deal":[75],"with":[76],"fashion":[78,146],"video.":[81],"Firstly,":[82],"introduce":[84],"visual-audio":[86],"composition":[87],"module":[88],"VACANet":[90],"aiming":[91],"distinguish":[93],"attentive":[94],"residual":[96],"entities":[97],"by":[98,117],"learning":[99],"embedding":[101],"both":[103],"streams.":[107],"Secondly,":[108],"alignment":[111,123],"training":[112],"scheme":[113],"is":[114],"then":[115],"designed":[116],"quality-aware":[118],"triplet":[119],"mining":[120],"domain":[122],"constraint":[124],"video-to-image":[126],"adaptation.":[127],"Finally,":[128],"extensive":[129],"experiments":[130],"conducted":[131],"challenging":[133],"datasets":[135],"demonstrate":[136],"scalable":[138],"effectiveness":[139],"our":[141],"model":[142],"alleviating":[144],"retrieval.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
