{"id":"https://openalex.org/W3083140956","doi":"https://doi.org/10.1109/tits.2020.3019390","title":"A Unified Multi-Task Learning Architecture for Fast and Accurate Pedestrian Detection","display_name":"A Unified Multi-Task Learning Architecture for Fast and Accurate Pedestrian Detection","publication_year":2020,"publication_date":"2020-09-04","ids":{"openalex":"https://openalex.org/W3083140956","doi":"https://doi.org/10.1109/tits.2020.3019390","mag":"3083140956"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2020.3019390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2020.3019390","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dr.ntu.edu.sg/bitstream/10356/147488/2/09186837.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022517034","display_name":"Chengju Zhou","orcid":"https://orcid.org/0000-0003-0795-4977"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Chengju Zhou","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038264463","display_name":"Meiqing Wu","orcid":"https://orcid.org/0000-0002-4978-2969"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Meiqing Wu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002694277","display_name":"Siew-Kei Lam","orcid":"https://orcid.org/0000-0002-8346-2635"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Siew-Kei Lam","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022517034"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.4915,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.66291089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"23","issue":"2","first_page":"982","last_page":"996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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/T10036","display_name":"Advanced Neural Network Applications","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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9991999864578247,"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/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"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/computer-science","display_name":"Computer science","score":0.8088064193725586},{"id":"https://openalex.org/keywords/pedestrian-detection","display_name":"Pedestrian detection","score":0.7876906394958496},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6961185336112976},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6663081049919128},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6557981371879578},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6543412208557129},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5034105181694031},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4850446581840515},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.47031059861183167},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4542050063610077},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4514275789260864},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43852829933166504},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41224798560142517},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41101184487342834},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3575456142425537},{"id":"https://openalex.org/keywords/pedestrian","display_name":"Pedestrian","score":0.24472680687904358},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0956200361251831}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8088064193725586},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.7876906394958496},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6961185336112976},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6663081049919128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6557981371879578},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6543412208557129},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5034105181694031},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4850446581840515},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.47031059861183167},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4542050063610077},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4514275789260864},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43852829933166504},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41224798560142517},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41101184487342834},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3575456142425537},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.24472680687904358},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0956200361251831},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tits.2020.3019390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2020.3019390","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/147488","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/147488","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/147488/2/09186837.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:dr.ntu.edu.sg:10356/147488","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/147488","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/147488/2/09186837.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G4722470142","display_name":null,"funder_award_id":"CREATE","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G8230782707","display_name":null,"funder_award_id":"TUMCREATE","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320323383","display_name":"Technische Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/02kkvpp62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3083140956.pdf","grobid_xml":"https://content.openalex.org/works/W3083140956.grobid-xml"},"referenced_works_count":77,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1507506748","https://openalex.org/W1686810756","https://openalex.org/W1896424170","https://openalex.org/W1903029394","https://openalex.org/W1964005749","https://openalex.org/W2031454541","https://openalex.org/W2074777933","https://openalex.org/W2097117768","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2111200615","https://openalex.org/W2125556102","https://openalex.org/W2143104527","https://openalex.org/W2143419558","https://openalex.org/W2150066425","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2216125271","https://openalex.org/W2251324968","https://openalex.org/W2340897893","https://openalex.org/W2490270993","https://openalex.org/W2497039038","https://openalex.org/W2531915888","https://openalex.org/W2560023338","https://openalex.org/W2594507094","https://openalex.org/W2624871570","https://openalex.org/W2752782242","https://openalex.org/W2762439315","https://openalex.org/W2765119169","https://openalex.org/W2792824754","https://openalex.org/W2798542761","https://openalex.org/W2798685991","https://openalex.org/W2803973142","https://openalex.org/W2809784273","https://openalex.org/W2883363148","https://openalex.org/W2894820835","https://openalex.org/W2895077992","https://openalex.org/W2896540732","https://openalex.org/W2910628332","https://openalex.org/W2913340405","https://openalex.org/W2916994131","https://openalex.org/W2962772649","https://openalex.org/W2962824366","https://openalex.org/W2962850098","https://openalex.org/W2963150697","https://openalex.org/W2963318220","https://openalex.org/W2963323244","https://openalex.org/W2963377935","https://openalex.org/W2963404857","https://openalex.org/W2963418739","https://openalex.org/W2963446712","https://openalex.org/W2963681621","https://openalex.org/W2963877604","https://openalex.org/W2963881378","https://openalex.org/W2963890956","https://openalex.org/W2963998989","https://openalex.org/W2964014730","https://openalex.org/W2964052344","https://openalex.org/W2970783474","https://openalex.org/W2982161360","https://openalex.org/W3001652308","https://openalex.org/W3141797743","https://openalex.org/W4293406525","https://openalex.org/W4300092737","https://openalex.org/W6637373629","https://openalex.org/W6640786210","https://openalex.org/W6717372056","https://openalex.org/W6718046261","https://openalex.org/W6739365718","https://openalex.org/W6741267457","https://openalex.org/W6743731764","https://openalex.org/W6744979068","https://openalex.org/W6750697433","https://openalex.org/W6752196072","https://openalex.org/W6753047673","https://openalex.org/W6769254149"],"related_works":["https://openalex.org/W2802018156","https://openalex.org/W2101531944","https://openalex.org/W4313315626","https://openalex.org/W2913302899","https://openalex.org/W2922437833","https://openalex.org/W4312696271","https://openalex.org/W4223892596","https://openalex.org/W2933098581","https://openalex.org/W2556125083","https://openalex.org/W3204901196"],"abstract_inverted_index":{"We":[0,133],"present":[1],"a":[2,22,56,86,111],"unified":[3,155],"multi-task":[4,32,156],"learning":[5,36,157],"architecture":[6,37,158,178],"for":[7,149],"fast":[8],"and":[9,40,48,79,199],"accurate":[10],"pedestrian":[11,46,165,212],"detection.":[12],"Different":[13],"from":[14,105],"existing":[15],"methods":[16,214],"which":[17,189],"often":[18],"focus":[19],"on":[20,197],"either":[21],"new":[23],"loss":[24],"function":[25],"or":[26],"architecture,":[27],"we":[28,54],"propose":[29],"an":[30,136],"improved":[31],"convolutional":[33,95],"neural":[34],"network":[35],"to":[38,61,74,89,114,142,162],"effectively":[39],"efficiently":[41],"interfuse":[42],"the":[43,76,94,102,106,119,129,144,176,192,207],"task":[44],"of":[45,146],"detection":[47,64,77,166,182,213,218],"semantic":[49,58,107,130],"segmentation.":[50],"To":[51],"achieve":[52,180],"this,":[53],"integrate":[55],"lightweight":[57],"segmentation":[59,108,131],"branch":[60],"Faster":[62],"R-CNN":[63],"framework":[65],"that":[66,203],"enables":[67],"end-to-end":[68],"hard":[69],"parameter":[70],"sharing":[71],"in":[72,97,122,167],"order":[73],"boost":[75],"performance":[78,183],"maintain":[80],"computational":[81,193],"efficiency":[82],"as":[83],"follows.":[84],"Firstly,":[85],"Semantic":[87,112],"Segmentation":[88,113],"Feature":[90],"Module":[91,116],"(SS2FM)":[92],"refines":[93,118],"features":[96,103],"RPN":[98,123],"stage":[99,124],"by":[100,125],"integrating":[101],"generated":[104],"branch.":[109],"Secondly,":[110],"Confidence":[115],"(SS2CM)":[117],"classification":[120],"confidence":[121],"fusing":[126],"it":[127],"with":[128,170,184],"confidence.":[132],"also":[134],"introduce":[135],"effective":[137],"anchor":[138],"matching":[139],"point":[140],"transform":[141],"alleviate":[143],"problem":[145],"feature":[147],"misalignment":[148],"heavily":[150],"occluded":[151],"pedestrians.":[152],"The":[153],"proposed":[154,177],"lends":[159],"itself":[160],"well":[161],"more":[163],"robust":[164],"diverse":[168],"scenarios":[169],"negligible":[171],"computation":[172],"overhead.":[173],"In":[174],"addition,":[175],"can":[179],"high":[181],"low":[185],"resolution":[186],"input":[187],"images,":[188],"significantly":[190],"reduces":[191],"complexity.":[194],"Experiment":[195],"results":[196],"CityPersons":[198],"Caltech":[200],"datasets":[201],"show":[202],"our":[204],"method":[205],"is":[206],"fastest":[208],"among":[209],"all":[210],"state-of-the-art":[211],"while":[215],"exhibiting":[216],"competitive":[217],"performance.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}