{"id":"https://openalex.org/W3215873667","doi":"https://doi.org/10.1145/3488904.3493379","title":"Leveraging Interpretability: Concept-based Pedestrian Detection with Deep Neural Networks","display_name":"Leveraging Interpretability: Concept-based Pedestrian Detection with Deep Neural Networks","publication_year":2021,"publication_date":"2021-11-25","ids":{"openalex":"https://openalex.org/W3215873667","doi":"https://doi.org/10.1145/3488904.3493379","mag":"3215873667"},"language":"en","primary_location":{"id":"doi:10.1145/3488904.3493379","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3488904.3493379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science in Cars Symposium","raw_type":"proceedings-article"},"type":"conference-paper","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/A5009219333","display_name":"Patrick Feifel","orcid":null},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Patrick Feifel","raw_affiliation_strings":["Stellantis, Opel Automobile GmbH, Germany and Carl von Ossietzky Universit\u00e4t Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellantis, Opel Automobile GmbH, Germany and Carl von Ossietzky Universit\u00e4t Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089224326","display_name":"Frank Bonarens","orcid":"https://orcid.org/0000-0003-3667-8211"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank Bonarens","raw_affiliation_strings":["Stellantis, Opel Automobile GmbH, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellantis, Opel Automobile GmbH, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073402824","display_name":"Frank K\u00f6ster","orcid":"https://orcid.org/0000-0001-8684-3698"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]},{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank K\u00f6ster","raw_affiliation_strings":["Deutsches Zentrum f\u00fcr Luft- und Raumfahrt, Germany and Carl von Ossietzky Universit\u00e4t Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt, Germany and Carl von Ossietzky Universit\u00e4t Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168","https://openalex.org/I2898391981"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1465,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42897966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9958999752998352,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9958999752998352,"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/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.9943000078201294,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.9488934278488159},{"id":"https://openalex.org/keywords/pedestrian","display_name":"Pedestrian","score":0.7492610216140747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.732658326625824},{"id":"https://openalex.org/keywords/pedestrian-detection","display_name":"Pedestrian detection","score":0.7229521870613098},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6430826187133789},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5128524303436279},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.49459215998649597},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49364909529685974},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42742636799812317},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11679345369338989},{"id":"https://openalex.org/keywords/transport-engineering","display_name":"Transport engineering","score":0.07412713766098022}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9488934278488159},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.7492610216140747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732658326625824},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.7229521870613098},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6430826187133789},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5128524303436279},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.49459215998649597},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49364909529685974},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42742636799812317},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11679345369338989},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.07412713766098022}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3488904.3493379","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3488904.3493379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science in Cars Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2933424091","display_name":null,"funder_award_id":"19A19005C","funder_id":"https://openalex.org/F4320323803","funder_display_name":"Bundesministerium f\u00fcr Wirtschaft und Energie"}],"funders":[{"id":"https://openalex.org/F4320323803","display_name":"Bundesministerium f\u00fcr Wirtschaft und Energie","ror":"https://ror.org/02vgg2808"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1987971958","https://openalex.org/W2031454541","https://openalex.org/W2107031757","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2563705555","https://openalex.org/W2592691248","https://openalex.org/W2594475271","https://openalex.org/W2594507094","https://openalex.org/W2626967530","https://openalex.org/W2741582944","https://openalex.org/W2774249462","https://openalex.org/W2786672974","https://openalex.org/W2896540732","https://openalex.org/W2945976633","https://openalex.org/W2961540362","https://openalex.org/W2963323244","https://openalex.org/W2963351448","https://openalex.org/W2963404857","https://openalex.org/W2963483561","https://openalex.org/W2963610729","https://openalex.org/W2963681621","https://openalex.org/W2964309882","https://openalex.org/W2970971581","https://openalex.org/W2971048680","https://openalex.org/W2986661129","https://openalex.org/W3002342835","https://openalex.org/W3007157104","https://openalex.org/W3041378136","https://openalex.org/W3082231033","https://openalex.org/W3092665420","https://openalex.org/W3095638603","https://openalex.org/W3101895620","https://openalex.org/W3112857588","https://openalex.org/W3137125108","https://openalex.org/W3177167524","https://openalex.org/W4289255206"],"related_works":["https://openalex.org/W2972620127","https://openalex.org/W2981141433","https://openalex.org/W4319993887","https://openalex.org/W4297789176","https://openalex.org/W2768346313","https://openalex.org/W2963249138","https://openalex.org/W2998594699","https://openalex.org/W4388585741","https://openalex.org/W4377865163","https://openalex.org/W3193857078"],"abstract_inverted_index":{"The":[0,83,123],"automation":[1],"of":[2,8,12,17,29,49,88,106,132,139,152,163],"driving":[3,169],"systems":[4],"relies":[5],"on":[6,104],"proof":[7],"the":[9,15,27,46,68,121,150],"correct":[10],"functioning":[11],"perception.":[13],"Arguing":[14],"safety":[16,47,137],"deep":[18],"neural":[19],"networks":[20],"(DNNs)":[21],"must":[22],"involve":[23],"quantifiable":[24],"evidence.":[25],"Currently,":[26],"application":[28],"DNNs":[30],"suffers":[31],"from":[32],"an":[33,39,92],"incomprehensible":[34],"behavior.":[35],"It":[36],"is":[37],"still":[38],"open":[40],"question":[41],"if":[42],"post-hoc":[43],"methods":[44],"mitigate":[45],"concerns":[48],"trained":[50],"DNNs.":[51],"Our":[52],"work":[53],"proposes":[54],"a":[55,99,136,140,164],"method":[56],"for":[57,77,118,142,149],"inherently":[58],"interpretable":[59,93],"and":[60,86],"concept-based":[61,158],"pedestrian":[62,143,153],"detection":[63],"(CPD).":[64],"CPD":[65,97,125,156],"explicitly":[66],"structures":[67],"latent":[69,89,107],"space":[70],"with":[71],"concept":[72,110],"vectors":[73],"that":[74,129],"learn":[75],"features":[76],"body":[78,100],"parts":[79],"as":[80],"predefined":[81],"concepts.":[82],"distance-based":[84],"clustering":[85],"separation":[87],"representations":[90,108],"build":[91],"reasoning":[94],"process.":[95],"Hence,":[96],"predicts":[98],"part":[101],"segmentation":[102],"based":[103],"distances":[105],"to":[109,160],"vectors.":[111],"A":[112],"non-interpretable":[113],"2d":[114],"bounding":[115],"box":[116],"prediction":[117],"pedestrians":[119],"complements":[120],"segmentation.":[122],"proposed":[124],"generates":[126],"additional":[127],"information":[128],"can":[130],"be":[131],"great":[133],"value":[134],"in":[135,167],"argumentation":[138],"DNN":[141],"detection.":[144,154],"We":[145],"report":[146],"competitive":[147],"performance":[148],"task":[151],"Finally,":[155],"enables":[157],"tests":[159],"quantify":[161],"evidence":[162],"safe":[165],"perception":[166],"automated":[168],"systems.":[170]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}