{"id":"https://openalex.org/W4304098258","doi":"https://doi.org/10.1145/3503161.3548274","title":"FastPR: One-stage Semantic Person Retrieval via Self-supervised Learning","display_name":"FastPR: One-stage Semantic Person Retrieval via Self-supervised Learning","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304098258","doi":"https://doi.org/10.1145/3503161.3548274"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548274","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548274","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548274","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548274","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085248515","display_name":"Meng Sun","orcid":"https://orcid.org/0000-0002-7435-3752"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Meng Sun","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015419107","display_name":"Ju Ren","orcid":"https://orcid.org/0000-0003-2782-183X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ju Ren","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022927606","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-0351-2939"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339293","display_name":"Wenwu Zhu","orcid":"https://orcid.org/0000-0003-2236-9290"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwu Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069049205","display_name":"Yaoxue Zhang","orcid":"https://orcid.org/0000-0001-6717-461X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoxue Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085248515"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.1199,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.41722515,"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":"3628","last_page":"3636"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998999834060669,"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/T10331","display_name":"Video Surveillance and Tracking Methods","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/T10812","display_name":"Human Pose and Action Recognition","score":0.9986000061035156,"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/T10036","display_name":"Advanced Neural Network Applications","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":0.8530838489532471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7010045051574707},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5733705163002014},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.537874698638916},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4884999990463257},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.41204190254211426},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40489551424980164},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.36979901790618896},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11924749612808228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8530838489532471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7010045051574707},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5733705163002014},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.537874698638916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4884999990463257},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.41204190254211426},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40489551424980164},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.36979901790618896},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11924749612808228},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548274","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548274","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548274","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3503161.3548274","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548274","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548274","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304098258.pdf","grobid_xml":"https://content.openalex.org/works/W4304098258.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1577581222","https://openalex.org/W2071462205","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2487442924","https://openalex.org/W2558661413","https://openalex.org/W2769112066","https://openalex.org/W2883311563","https://openalex.org/W2888166343","https://openalex.org/W2894786240","https://openalex.org/W2913939497","https://openalex.org/W2940092410","https://openalex.org/W2952524542","https://openalex.org/W2963037989","https://openalex.org/W2963420272","https://openalex.org/W2964121906","https://openalex.org/W2980088508","https://openalex.org/W2985951359","https://openalex.org/W2990138404","https://openalex.org/W3005971801","https://openalex.org/W3015686580","https://openalex.org/W3024059432","https://openalex.org/W3108655343","https://openalex.org/W3121021526","https://openalex.org/W3154430790","https://openalex.org/W3173151551","https://openalex.org/W3202473909","https://openalex.org/W3206868111"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W1972035260","https://openalex.org/W4321636575","https://openalex.org/W1986418932","https://openalex.org/W2357796999","https://openalex.org/W2045526782","https://openalex.org/W2741131631","https://openalex.org/W1986106996","https://openalex.org/W4285012873","https://openalex.org/W2122517733"],"abstract_inverted_index":{"Semantic":[0],"person":[1,8,82,91,153,171,197],"retrieval":[2,83,95,209],"aims":[3],"to":[4,88,109,121,163,184,212],"locate":[5],"a":[6,32,41,79,100,116,147,151,178,199],"specific":[7],"in":[9,23,68,172,198],"an":[10,158],"image":[11],"with":[12,40,217],"the":[13,38,47,50,69,74,90,111,123,128,141,165,169,173,186,195,207,213],"query":[14],"of":[15,168,190],"semantic":[16,81,94],"descriptions,":[17],"which":[18,105],"has":[19],"shown":[20],"great":[21],"significance":[22],"surveillance":[24,132],"and":[25,44,60,93,114,138,140,193],"security":[26],"applications.":[27],"Prior":[28],"arts":[29],"commonly":[30],"adopt":[31],"two-stage":[33,70],"method":[34,84],"that":[35,130,204],"first":[36],"extracts":[37],"persons":[39,143],"pretrained":[42],"detector":[43],"then":[45],"finds":[46],"target":[48,142,170,196],"matching":[49],"descriptions":[51],"optimally.However,":[52],"existing":[53],"works":[54],"suffer":[55,135],"from":[56,136],"high":[57],"computational":[58],"complexity":[59],"low":[61],"recall":[62],"rate":[63],"caused":[64],"by":[65,177],"error":[66],"accumulation":[67],"inference.":[71],"To":[72,126],"solve":[73],"problems,":[75],"we":[76,98],"propose":[77,99,150],"FastPR,":[78],"one-stage":[80],"via":[85],"self-supervised":[86],"learning,":[87],"optimize":[89],"localization":[92,154,187],"simultaneously.":[96],"Specifically,":[97],"dynamic":[101],"visual-semantic":[102],"alignment":[103],"mechanism":[104],"utilizes":[106],"grid-based":[107],"attention":[108,124],"fuse":[110],"cross-modal":[112],"features,":[113,175],"employs":[115],"label":[117],"prediction":[118,181],"proxy":[119,161,182],"task":[120,162,183],"constrain":[122],"process.":[125],"tackle":[127],"challenges":[129],"real-world":[131],"images":[133],"may":[134,144],"low-resolution":[137],"occlusion,":[139],"be":[145],"within":[146],"crowd,we":[148],"further":[149],"dual-granularity":[152],"module":[155],"through":[156],"designing":[157],"upsampling":[159],"reconstruction":[160],"enhance":[164],"local":[166],"feature":[167],"fused":[174],"followed":[176],"tailored":[179],"offset":[180],"make":[185],"network":[188],"capable":[189],"accurately":[191],"identifying":[192],"distinguishing":[194],"crowd.":[200],"Experimental":[201],"results":[202],"demonstrate":[203],"FastPR":[205],"achieves":[206],"best":[208],"accuracy":[210],"compared":[211],"state-of-the-art":[214],"baseline":[215],"methods,":[216],"over":[218],"15":[219],"times":[220],"inference":[221],"time":[222],"reduction.":[223]},"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"}