{"id":"https://openalex.org/W3171752591","doi":"https://doi.org/10.1145/3460426.3463588","title":"NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection","display_name":"NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3171752591","doi":"https://doi.org/10.1145/3460426.3463588","mag":"3171752591"},"language":"en","primary_location":{"id":"doi:10.1145/3460426.3463588","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.02426","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zekun Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zekun Luo","raw_affiliation_strings":["Youtu Lab & Tencent, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Youtu Lab & Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zheng Fang","orcid":null},"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":"Zheng Fang","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sixiao Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sixiao Zheng","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yabiao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabiao Wang","raw_affiliation_strings":["Youtu Lab & Tencent, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Youtu Lab & Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yanwei Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Fu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":2.6162,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.9150581,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"481","last_page":"485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9997000098228455,"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/T10331","display_name":"Video Surveillance and Tracking Methods","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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12597","display_name":"Fire Detection and Safety Systems","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.7020999789237976},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5508999824523926},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4814999997615814},{"id":"https://openalex.org/keywords/false-positives-and-false-negatives","display_name":"False positives and false negatives","score":0.41940000653266907},{"id":"https://openalex.org/keywords/pedestrian-detection","display_name":"Pedestrian detection","score":0.41780000925064087},{"id":"https://openalex.org/keywords/pedestrian","display_name":"Pedestrian","score":0.39559999108314514},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3652999997138977}],"concepts":[{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.7020999789237976},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6664999723434448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6137999892234802},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5558000206947327},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5508999824523926},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C112789634","wikidata":"https://www.wikidata.org/wiki/Q18207010","display_name":"False positives and false negatives","level":3,"score":0.41940000653266907},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.41780000925064087},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C2989486834","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"True positive rate","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25619998574256897},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3460426.3463588","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.02426","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.02426","pdf_url":"https://arxiv.org/pdf/2106.02426","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.02426","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.02426","pdf_url":"https://arxiv.org/pdf/2106.02426","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2031454541","https://openalex.org/W2105610271","https://openalex.org/W2107775979","https://openalex.org/W2125556102","https://openalex.org/W2159386181","https://openalex.org/W2161969291","https://openalex.org/W2168356304","https://openalex.org/W2609144136","https://openalex.org/W2883363148","https://openalex.org/W2896540732","https://openalex.org/W2963318220","https://openalex.org/W2963404857","https://openalex.org/W2963681621","https://openalex.org/W2963998989","https://openalex.org/W2964121718","https://openalex.org/W2997258722","https://openalex.org/W2997344726","https://openalex.org/W3034638324","https://openalex.org/W6669153968"],"related_works":[],"abstract_inverted_index":{"Non-Maximum":[0],"Suppression":[1],"(NMS)":[2],"is":[3,73,78],"essential":[4],"for":[5],"object":[6],"detection":[7],"and":[8,18,41,48,76,100,138],"affects":[9],"the":[10,32,38,42,54,93,119],"evaluation":[11,43],"results":[12,115,129],"by":[13,46,81],"incorporating":[14],"False":[15,19],"Positives":[16],"(FP)":[17],"Negatives":[20],"(FN),":[21],"especially":[22],"in":[23],"crowd":[24],"occlusion":[25],"scenes.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30,84],"raise":[31],"problem":[33],"of":[34,121,133],"weak":[35],"connection":[36],"between":[37],"training":[39],"targets":[40,109],"metrics":[44],"caused":[45],"NMS":[47,55],"propose":[49,85],"a":[50,86,101],"novel":[51],"NMS-Loss":[52,67],"making":[53],"procedure":[56],"can":[57],"be":[58],"trained":[59],"end-to-end":[60],"without":[61],"any":[62],"additional":[63],"network":[64],"parameters.":[65],"Our":[66],"punishes":[68],"two":[69],"cases":[70],"when":[71],"FP":[72],"not":[74],"suppressed":[75],"FN":[77],"wrongly":[79],"eliminated":[80],"NMS.":[82],"Specifically,":[83],"pull":[87,90],"loss":[88,103],"to":[89,97,104],"predictions":[91,106],"with":[92,107,118,130],"same":[94],"target":[95],"close":[96],"each":[98,112],"other,":[99],"push":[102,105],"different":[108],"away":[110],"from":[111],"other.":[113],"Experimental":[114],"show":[116],"that":[117],"help":[120],"NMS-Loss,":[122],"our":[123],"detector,":[124],"namely":[125],"NMS-Ped,":[126],"achieves":[127],"impressive":[128],"Miss":[131],"Rate":[132],"5.92%":[134],"on":[135],"Caltech":[136],"dataset":[137],"10.08%on":[139],"CityPersons":[140],"dataset,":[141],"which":[142],"are":[143],"both":[144],"better":[145],"than":[146],"state-of-the-art":[147],"competitors.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2021-06-22T00:00:00"}