{"id":"https://openalex.org/W2984664372","doi":"https://doi.org/10.1109/wacv45572.2020.9093560","title":"Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion","display_name":"Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W2984664372","doi":"https://doi.org/10.1109/wacv45572.2020.9093560","mag":"2984664372"},"language":"en","primary_location":{"id":"doi:10.1109/wacv45572.2020.9093560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.11826","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084928022","display_name":"Adam Kortylewski","orcid":"https://orcid.org/0000-0002-9146-4403"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Kortylewski","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345153","display_name":"Qing Liu","orcid":"https://orcid.org/0000-0001-5286-4423"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing Liu","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100670142","display_name":"Huiyu Wang","orcid":"https://orcid.org/0000-0002-6622-3579"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huiyu Wang","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004325726","display_name":"Zhishuai Zhang","orcid":"https://orcid.org/0000-0002-1013-0322"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhishuai Zhang","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086706224","display_name":"Alan Yuille","orcid":"https://orcid.org/0000-0001-5207-9249"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan Yuille","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1322","last_page":"1330"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","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"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","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/T10036","display_name":"Advanced Neural Network Applications","score":0.9984999895095825,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.9097981452941895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.8145294189453125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7495291233062744},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7110530734062195},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6649196743965149},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6346434950828552},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47463640570640564},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4260827898979187},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4254567325115204},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.41156670451164246},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.31580090522766113}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9097981452941895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8145294189453125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7495291233062744},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7110530734062195},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6649196743965149},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6346434950828552},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47463640570640564},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4260827898979187},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4254567325115204},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.41156670451164246},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31580090522766113}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/wacv45572.2020.9093560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.11826","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.11826","pdf_url":"https://arxiv.org/pdf/1905.11826","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"},{"id":"doi:10.48550/arxiv.1905.11826","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.11826","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2984664372","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.11826","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.11826","pdf_url":"https://arxiv.org/pdf/1905.11826","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2984664372.pdf","grobid_xml":"https://content.openalex.org/works/W2984664372.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1635415043","https://openalex.org/W1686810756","https://openalex.org/W1821057786","https://openalex.org/W1899185266","https://openalex.org/W1991264156","https://openalex.org/W2089779414","https://openalex.org/W2108598243","https://openalex.org/W2126747264","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2530184277","https://openalex.org/W2549047603","https://openalex.org/W2552264258","https://openalex.org/W2560977758","https://openalex.org/W2613282858","https://openalex.org/W2746314669","https://openalex.org/W2764024122","https://openalex.org/W2765332150","https://openalex.org/W2768161499","https://openalex.org/W2796249144","https://openalex.org/W2805881302","https://openalex.org/W2943892363","https://openalex.org/W2944223741","https://openalex.org/W2962790345","https://openalex.org/W2964222561","https://openalex.org/W6636752644","https://openalex.org/W6637373629","https://openalex.org/W6639927594","https://openalex.org/W6684191040","https://openalex.org/W6727785890","https://openalex.org/W6729484714","https://openalex.org/W6730178624","https://openalex.org/W6739381556","https://openalex.org/W6745777441","https://openalex.org/W6752288430"],"related_works":["https://openalex.org/W2946915130","https://openalex.org/W2977637882","https://openalex.org/W2796249144","https://openalex.org/W2746314669","https://openalex.org/W1991264156","https://openalex.org/W1686810756","https://openalex.org/W3011334834","https://openalex.org/W2971358443","https://openalex.org/W2944223741","https://openalex.org/W2552264258","https://openalex.org/W2194775991","https://openalex.org/W2126747264","https://openalex.org/W2108598243","https://openalex.org/W2089779414","https://openalex.org/W1821057786","https://openalex.org/W1635415043","https://openalex.org/W2991523156","https://openalex.org/W3004918189","https://openalex.org/W2912510623","https://openalex.org/W2151102638"],"abstract_inverted_index":{"Deep":[0],"convolutional":[1],"neural":[2],"networks":[3],"(DCNNs)":[4],"are":[5,40,47,182],"powerful":[6],"models":[7,39,63,133,195],"that":[8,20,74,109,192],"yield":[9],"impressive":[10],"results":[11,190],"at":[12,229],"object":[13,62,114,126],"classification.":[14,98],"However,":[15],"recent":[16],"work":[17],"has":[18,219],"shown":[19],"they":[21,46],"do":[22],"not":[23,48,220],"generalize":[24],"well":[25],"to":[26,31,36,42,64,77,134,146,174,207,223],"partially":[27,176],"occluded":[28,177,214,224],"objects":[29,225],"and":[30,60,80,117,196],"mask":[32,81],"attacks.":[33,82],"In":[34,54],"contrast":[35],"DCNNs,":[37],"compositional":[38,61,132,186,194],"robust":[41,76],"partial":[43,78],"occlusion,":[44],"however,":[45],"as":[49,51],"discriminative":[50,72,235],"deep":[52,204],"models.":[53],"this":[55],"work,":[56],"we":[57,100],"combine":[58],"DC-NNs":[59],"retain":[65],"the":[66,102,110,119,140,149,163,185,230],"best":[67],"of":[68,122,131,152,202],"both":[69],"approaches:":[70],"a":[71,91,166,199],"model":[73,84,212],"is":[75,85,94,159,172],"occlusion":[79],"Our":[83,188],"learned":[86],"in":[87,139,148,165,180],"two":[88],"steps.":[89],"First,":[90],"standard":[92],"DCNN":[93,103,164],"trained":[95],"for":[96,124,136,237],"image":[97,158],"Subsequently,":[99],"cluster":[101],"features":[104],"into":[105],"dictionaries.":[106],"We":[107,128],"show":[108],"dictionary":[111],"components":[112],"resemble":[113],"part":[115],"detectors":[116],"learn":[118],"spatial":[120,141],"distribution":[121],"parts":[123],"each":[125],"class.":[127],"propose":[129],"mixtures":[130],"account":[135],"large":[137],"changes":[138,147],"activation":[142],"patterns":[143],"(e.g.":[144],"due":[145],"3D":[150],"pose":[151],"an":[153,157],"object).":[154],"At":[155],"runtime,":[156],"first":[160],"classified":[161,183],"by":[162,184],"feedforward":[167],"manner.":[168],"The":[169,210],"prediction":[170],"uncertainty":[171],"used":[173],"detect":[175],"objects,":[178,215],"which":[179],"turn":[181],"model.":[187],"experimental":[189],"demonstrate":[191],"combining":[193],"DCNNs":[197],"resolves":[198],"fundamental":[200],"problem":[201],"current":[203],"learning":[205],"approaches":[206],"computer":[208],"vision:":[209],"combined":[211],"recognizes":[213],"even":[216],"when":[217],"it":[218],"been":[221],"exposed":[222],"during":[226],"training,":[227],"while":[228],"same":[231],"time":[232],"maintaining":[233],"high":[234],"performance":[236],"non-occluded":[238],"objects.":[239]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-09-27T00:00:00"}