{"id":"https://openalex.org/W2962870549","doi":"https://doi.org/10.1109/tpami.2018.2863285","title":"Deep Supervision with Intermediate Concepts","display_name":"Deep Supervision with Intermediate Concepts","publication_year":2018,"publication_date":"2018-08-13","ids":{"openalex":"https://openalex.org/W2962870549","doi":"https://doi.org/10.1109/tpami.2018.2863285","mag":"2962870549","pmid":"https://pubmed.ncbi.nlm.nih.gov/30106706"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2018.2863285","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2018.2863285","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/8752185/08434117.pdf","source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/34/8752185/08434117.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100351597","display_name":"Chi Li","orcid":"https://orcid.org/0000-0002-5957-5680"},"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":"Chi Li","raw_affiliation_strings":["Computer Science, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-5957-5680","affiliations":[{"raw_affiliation_string":"Computer Science, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101510045","display_name":"M. Zeeshan Zia","orcid":"https://orcid.org/0000-0001-8221-2637"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Zeeshan Zia","raw_affiliation_strings":["Hololens, Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8221-2637","affiliations":[{"raw_affiliation_string":"Hololens, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000328580","display_name":"Quoc-Huy Tran","orcid":"https://orcid.org/0000-0003-1396-6544"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quoc-Huy Tran","raw_affiliation_strings":["Media Analytics, NEC Laboratories America Inc, Cupertino, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1396-6544","affiliations":[{"raw_affiliation_string":"Media Analytics, NEC Laboratories America Inc, Cupertino, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101426810","display_name":"Xiang Yu","orcid":"https://orcid.org/0000-0001-9431-5131"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Yu","raw_affiliation_strings":["Media Analytics, NEC Laboratories America Inc, Cupertino, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media Analytics, NEC Laboratories America Inc, Cupertino, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041383246","display_name":"Gregory D. Hager","orcid":"https://orcid.org/0000-0002-6662-9763"},"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":"Gregory D. Hager","raw_affiliation_strings":["Department of Computer Science, The Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-6662-9763","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046609009","display_name":"Manmohan Chandraker","orcid":"https://orcid.org/0000-0003-4683-2454"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manmohan Chandraker","raw_affiliation_strings":["Media Analytics, NEC Laboratories America Inc, Cupertino, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media Analytics, NEC Laboratories America Inc, Cupertino, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9132,"has_fulltext":true,"cited_by_count":86,"citation_normalized_percentile":{"value":0.9370543,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"41","issue":"8","first_page":"1828","last_page":"1843"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10531","display_name":"Advanced Vision and Imaging","score":0.998199999332428,"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":0.7953203916549683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.755574107170105},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7452014088630676},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6900226473808289},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.638957142829895},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5806439518928528},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5507602691650391},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5145963430404663},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5112848281860352},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5022385120391846},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4371687173843384},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42455294728279114},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4139171242713928},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36114227771759033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7953203916549683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.755574107170105},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7452014088630676},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6900226473808289},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.638957142829895},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5806439518928528},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5507602691650391},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5145963430404663},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5112848281860352},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5022385120391846},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4371687173843384},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42455294728279114},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4139171242713928},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36114227771759033},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2018.2863285","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2018.2863285","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/8752185/08434117.pdf","source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:30106706","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30106706","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":{"id":"doi:10.1109/tpami.2018.2863285","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2018.2863285","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/8752185/08434117.pdf","source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2456170329","display_name":"NRI: Collaborative Research: Experiential Learning for Robots: From Physics to Actions to Tasks","funder_award_id":"1637949","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962870549.pdf","grobid_xml":"https://content.openalex.org/works/W2962870549.grobid-xml"},"referenced_works_count":94,"referenced_works":["https://openalex.org/W64813323","https://openalex.org/W1513966746","https://openalex.org/W1519402791","https://openalex.org/W1533861849","https://openalex.org/W1591870335","https://openalex.org/W1686810756","https://openalex.org/W1691728462","https://openalex.org/W1770712749","https://openalex.org/W1814328102","https://openalex.org/W1836465849","https://openalex.org/W1893585201","https://openalex.org/W1893912098","https://openalex.org/W1896424170","https://openalex.org/W1946609740","https://openalex.org/W1949285675","https://openalex.org/W1949483711","https://openalex.org/W1985217382","https://openalex.org/W1991264156","https://openalex.org/W1994529670","https://openalex.org/W2010625607","https://openalex.org/W2013397696","https://openalex.org/W2019101221","https://openalex.org/W2046175448","https://openalex.org/W2071634722","https://openalex.org/W2081519360","https://openalex.org/W2085805060","https://openalex.org/W2095268271","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2117766076","https://openalex.org/W2119414364","https://openalex.org/W2137278143","https://openalex.org/W2137983211","https://openalex.org/W2150066425","https://openalex.org/W2159187711","https://openalex.org/W2162888803","https://openalex.org/W2163605009","https://openalex.org/W2168894214","https://openalex.org/W2190691619","https://openalex.org/W2194775991","https://openalex.org/W2237537322","https://openalex.org/W2278156142","https://openalex.org/W2302255633","https://openalex.org/W2342277278","https://openalex.org/W2345945060","https://openalex.org/W2412002662","https://openalex.org/W2474531669","https://openalex.org/W2487365028","https://openalex.org/W2495603374","https://openalex.org/W2548197316","https://openalex.org/W2578075911","https://openalex.org/W2614311475","https://openalex.org/W2913340405","https://openalex.org/W2949117887","https://openalex.org/W2950678851","https://openalex.org/W2952074561","https://openalex.org/W2962809185","https://openalex.org/W2963037478","https://openalex.org/W2963730200","https://openalex.org/W2964057995","https://openalex.org/W3104240813","https://openalex.org/W3106165820","https://openalex.org/W3118608800","https://openalex.org/W3137695714","https://openalex.org/W3146803896","https://openalex.org/W4242599633","https://openalex.org/W4293052488","https://openalex.org/W4297692481","https://openalex.org/W4300537377","https://openalex.org/W4394671432","https://openalex.org/W6631135043","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6637412569","https://openalex.org/W6637849068","https://openalex.org/W6638667902","https://openalex.org/W6639495226","https://openalex.org/W6641001580","https://openalex.org/W6680171035","https://openalex.org/W6684191040","https://openalex.org/W6684665197","https://openalex.org/W6685315510","https://openalex.org/W6687484953","https://openalex.org/W6690067395","https://openalex.org/W6698183232","https://openalex.org/W6703956885","https://openalex.org/W6719936175","https://openalex.org/W6722836162","https://openalex.org/W6723438068","https://openalex.org/W6732004936","https://openalex.org/W6763485134","https://openalex.org/W6764072534","https://openalex.org/W6785867886","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W1663079876","https://openalex.org/W2069133146","https://openalex.org/W2017545316","https://openalex.org/W2100576949","https://openalex.org/W2159686533","https://openalex.org/W2493838176","https://openalex.org/W4297686120","https://openalex.org/W4377086356","https://openalex.org/W3042419602","https://openalex.org/W2966649771"],"abstract_inverted_index":{"Recent":[0],"data-driven":[1],"approaches":[2],"to":[3,45,54,118,138],"scene":[4],"interpretation":[5],"predominantly":[6],"pose":[7],"inference":[8,47],"as":[9,179],"an":[10,46,62],"end-to-end":[11],"black-box":[12],"mapping,":[13],"commonly":[14],"performed":[15],"by":[16,73],"a":[17,78,92],"Convolutional":[18],"Neural":[19],"Network":[20],"(CNN).":[21],"However,":[22],"decades":[23],"of":[24,77,110,125,147,176],"work":[25],"on":[26,154],"perceptual":[27],"organization":[28],"in":[29,88],"both":[30],"human":[31],"and":[32,49,99,151,164],"machine":[33],"vision":[34],"suggest":[35],"that":[36,42,83,114,170],"there":[37],"are":[38,43,85,116],"often":[39],"intermediate":[40,81],"representations":[41],"intrinsic":[44],"task,":[48],"which":[50,95],"provide":[51,167],"essential":[52],"structure":[53,68],"improve":[55],"generalization.":[56],"In":[57],"this":[58,104,111],"work,":[59],"we":[60,115],"explore":[61],"approach":[63,112,172],"for":[64],"injecting":[65],"prior":[66],"domain":[67],"into":[69],"neural":[70],"network":[71],"training":[72],"supervising":[74],"hidden":[75],"layers":[76],"CNN":[79],"with":[80],"concepts":[82],"normally":[84],"not":[86],"observed":[87],"practice.":[89],"We":[90,166],"formulate":[91],"probabilistic":[93],"framework":[94],"formalizes":[96],"these":[97],"notions":[98],"predicts":[100],"improved":[101],"generalization":[102],"via":[103],"deep":[105],"supervision":[106],"method.":[107],"One":[108],"advantage":[109],"is":[113],"able":[117],"train":[119],"only":[120],"from":[121],"synthetic":[122],"CAD":[123],"renderings":[124],"cluttered":[126],"scenes,":[127],"where":[128],"concept":[129],"values":[130],"can":[131],"be":[132],"extracted,":[133],"but":[134],"apply":[135],"the":[136,144],"results":[137],"real":[139,155],"images.":[140],"Our":[141],"implementation":[142],"achieves":[143],"state-of-the-art":[145],"performance":[146],"2D/3D":[148],"keypoint":[149],"localization":[150],"image":[152,156],"classification":[153],"benchmarks":[157],"including":[158],"KITTI,":[159],"PASCAL":[160],"VOC,":[161],"PASCAL3D+,":[162],"IKEA,":[163],"CIFAR100.":[165],"additional":[168],"evidence":[169],"our":[171],"outperforms":[173],"alternative":[174],"forms":[175],"supervision,":[177],"such":[178],"multi-task":[180],"networks.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
