{"id":"https://openalex.org/W3092711952","doi":"https://doi.org/10.1145/3394171.3414455","title":"A Cross-modality and Progressive Person Search System","display_name":"A Cross-modality and Progressive Person Search System","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3092711952","doi":"https://doi.org/10.1145/3394171.3414455","mag":"3092711952"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3414455","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3414455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th 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/A5100373745","display_name":"Xiaohong Chen","orcid":"https://orcid.org/0000-0002-9797-8384"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaodong Chen","raw_affiliation_strings":["University of Science and Technology of China, He Fei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, He Fei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068917997","display_name":"Wu Liu","orcid":"https://orcid.org/0000-0003-1633-7575"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Liu","raw_affiliation_strings":["AI Research of JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Research of JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030704926","display_name":"Xinchen Liu","orcid":"https://orcid.org/0000-0003-4931-8821"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinchen Liu","raw_affiliation_strings":["AI Research of JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Research of JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["University of Science and Technology of China, He Fei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, He Fei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017597537","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0003-2497-7732"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["AI Research of JD.com, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Research of JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100373745"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.2931,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.57207434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4550","last_page":"4552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998000264167786,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998000264167786,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9968000054359436,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9962999820709229,"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":0.8420001268386841},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.672730565071106},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5224655866622925},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5214009284973145},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5119487047195435},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.492738276720047},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4719761312007904},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4419298470020294},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4407097399234772},{"id":"https://openalex.org/keywords/visual-search","display_name":"Visual search","score":0.4374564290046692},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4318406283855438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4239354133605957},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34566524624824524},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14232823252677917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8420001268386841},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.672730565071106},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5224655866622925},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5214009284973145},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5119487047195435},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.492738276720047},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4719761312007904},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4419298470020294},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4407097399234772},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.4374564290046692},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4318406283855438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4239354133605957},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34566524624824524},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14232823252677917},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3414455","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3414455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2049892260","https://openalex.org/W2064675550","https://openalex.org/W2193413348","https://openalex.org/W2579549467","https://openalex.org/W2592388817","https://openalex.org/W2782217382","https://openalex.org/W2795758732","https://openalex.org/W2797394071","https://openalex.org/W2798775284","https://openalex.org/W2801814609","https://openalex.org/W2938085446","https://openalex.org/W2951343884","https://openalex.org/W2962691289","https://openalex.org/W2963163009","https://openalex.org/W2963322158","https://openalex.org/W2963330186","https://openalex.org/W2963341956","https://openalex.org/W2963449390","https://openalex.org/W2963805953","https://openalex.org/W2963842104","https://openalex.org/W2963882743","https://openalex.org/W2965099462","https://openalex.org/W2981357180","https://openalex.org/W2981538481","https://openalex.org/W2989980422","https://openalex.org/W2990317318","https://openalex.org/W3040248848","https://openalex.org/W3046890131","https://openalex.org/W3100506510","https://openalex.org/W4299670242","https://openalex.org/W4300106007","https://openalex.org/W6600297362"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935"],"abstract_inverted_index":{"This":[0],"demonstration":[1],"presents":[2],"an":[3],"instant":[4,72],"and":[5,73,81],"progressive":[6,74],"cross-modality":[7],"person":[8,36,75,99,186],"search":[9,37,76,114],"system,":[10,15],"called":[11],"'CMPS'.":[12],"Through":[13],"the":[14,20,47,57,68,78,87,91,95,101,112,119,123,129,145,150,165,176,180,184,190,194],"users":[16],"can":[17,136,152,167,196],"instantly":[18],"find":[19,46],"lost":[21,185],"children":[22],"or":[23],"elderly":[24],"persons":[25],"by":[26,108,117,187],"simply":[27],"describing":[28],"their":[29,155],"appearance":[30,96],"through":[31,157],"speech.":[32,158],"Unlike":[33],"most":[34],"existing":[35],"applications":[38],"which":[39],"have":[40],"to":[41,45,103],"cost":[42],"much":[43],"time":[44,55],"probe":[48],"images,":[49],"CMPS":[50,64,207],"will":[51,178],"save":[52],"more":[53],"valuable":[54],"in":[56,128,201],"early":[58],"stage":[59],"of":[60,67,97,126,183,206],"losing.":[61],"The":[62,133],"proposed":[63],"is":[65,115,163,208],"one":[66],"first":[69,89],"attempts":[70],"towards":[71],"leveraging":[77],"audio,":[79],"text,":[80],"visual":[82,124],"modalities":[83],"together.":[84],"In":[85],"detail,":[86],"system":[88,177,195],"takes":[90],"speech":[92],"that":[93],"describes":[94],"a":[98,105,160,172],"as":[100,139,171],"input":[102],"obtain":[104],"textual":[106,120],"description":[107,156],"speech-to-text":[109],"conversion.":[110],"Then":[111],"cross-modal":[113],"performed":[116],"matching":[118],"embedding":[121],"with":[122],"representations":[125],"images":[127,135],"learned":[130],"latent":[131],"space.":[132],"searched":[134],"be":[137],"used":[138],"candidates":[140,146],"for":[141],"query":[142],"expansion.":[143],"If":[144],"are":[147],"not":[148],"right,":[149],"user":[151,166],"quickly":[153],"adjust":[154],"Once":[159],"right":[161],"image":[162],"found,":[164],"directly":[168],"click":[169],"it":[170],"new":[173],"query.":[174],"Finally":[175],"give":[179],"complete":[181],"track":[182],"once-click.":[188],"On":[189],"built":[191],"CUHK-PEDES-AUDIOS":[192],"dataset,":[193],"achieve":[197],"82.46%":[198],"rank-1":[199],"accuracy":[200],"real-time":[202],"speed.":[203],"Our":[204],"code":[205],"available":[209],"at":[210],"https://github.com/SheldongChen/Search-People-With-Audio.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
