{"id":"https://openalex.org/W2249646774","doi":null,"title":"Learning Features and Parts for Fine-Grained Recognition (Invited Paper)","display_name":"Learning Features and Parts for Fine-Grained Recognition (Invited Paper)","publication_year":2015,"publication_date":"2015-11-21","ids":{"openalex":"https://openalex.org/W2249646774","mag":"2249646774"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.695.7818","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.695.7818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vision.stanford.edu/pdf/icpr14.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5060909587","display_name":"Jonathan Krause","orcid":"https://orcid.org/0009-0002-8762-6614","observed_orcids":["https://orcid.org/0009-0002-8762-6614","https://orcid.org/0000-0002-1952-3480"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Krause","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089275971","display_name":"Timnit Gebru","orcid":"https://orcid.org/0009-0007-4814-1944","observed_orcids":["https://orcid.org/0009-0007-4814-1944"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timnit Gebru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101542158","display_name":"Jia Deng","orcid":"https://orcid.org/0000-0001-9594-4554","observed_orcids":["https://orcid.org/0000-0001-9594-4554"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Deng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009049500","display_name":"Li-Jia Li","orcid":"https://orcid.org/0000-0001-5850-7013","observed_orcids":["https://orcid.org/0000-0001-5850-7013"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li-jia Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100450462","display_name":"Li Fei-Fei","orcid":"https://orcid.org/0000-0002-7481-0810","observed_orcids":["https://orcid.org/0000-0002-7481-0810","https://orcid.org/0000-0001-7652-0473"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Fei-fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.6807000041007996,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.6807000041007996,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.27730000019073486,"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":0.03229999914765358,"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/fine-grained-classification","display_name":"fine-grained classification","score":0.9919999837875366},{"id":"https://openalex.org/keywords/part-detection","display_name":"part detection","score":0.6380000114440918},{"id":"https://openalex.org/keywords/appearance-descriptors","display_name":"appearance descriptors","score":0.7379999756813049},{"id":"https://openalex.org/keywords/object-representation","display_name":"object representation","score":0.6570000052452087},{"id":"https://openalex.org/keywords/image-level-labels","display_name":"image-level labels","score":0.753000020980835},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.7300000190734863},{"id":"https://openalex.org/keywords/bird-identification","display_name":"bird identification","score":0.7440000176429749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5077670812606812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42950624227523804}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.695.7818","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.695.7818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vision.stanford.edu/pdf/icpr14.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W14333344","https://openalex.org/W1531492214","https://openalex.org/W1797268635","https://openalex.org/W1846799578","https://openalex.org/W1977295328","https://openalex.org/W1994213117","https://openalex.org/W1995318441","https://openalex.org/W1995543189","https://openalex.org/W2005286252","https://openalex.org/W2045750950","https://openalex.org/W2083367367","https://openalex.org/W2084435358","https://openalex.org/W2091759811","https://openalex.org/W2097033479","https://openalex.org/W2103490241","https://openalex.org/W2108598243","https://openalex.org/W2110015572","https://openalex.org/W2110765924","https://openalex.org/W2112796928","https://openalex.org/W2114705035","https://openalex.org/W2118696714","https://openalex.org/W2119525058","https://openalex.org/W2124351162","https://openalex.org/W2135706578","https://openalex.org/W2138011018","https://openalex.org/W2147238549","https://openalex.org/W2151103935","https://openalex.org/W2152411181","https://openalex.org/W2155541015","https://openalex.org/W2157558673","https://openalex.org/W2161969291","https://openalex.org/W2162915993","https://openalex.org/W2163605009","https://openalex.org/W2168356304","https://openalex.org/W2169501191","https://openalex.org/W2229419338","https://openalex.org/W2535410496"],"related_works":["https://openalex.org/W2155839910","https://openalex.org/W6983053826","https://openalex.org/W2887325227","https://openalex.org/W2295416420","https://openalex.org/W2595051209","https://openalex.org/W2207849498","https://openalex.org/W2807742018","https://openalex.org/W2521868378","https://openalex.org/W3208400097","https://openalex.org/W56385144"],"abstract_inverted_index":{"Abstract\u2014This":[0],"paper":[1],"addresses":[2],"the":[3,62,77],"problem":[4],"of":[5,101],"fine-grained":[6,48,74,126],"recognition:":[7],"recognizing":[8],"subordinate":[9],"categories":[10],"such":[11],"as":[12],"bird":[13],"species,":[14],"car":[15],"models,":[16],"or":[17,104],"dog":[18],"breeds.":[19],"We":[20,113],"focus":[21],"on":[22,61],"two":[23,119],"major":[24],"challenges:":[25],"learning":[26],"expressive":[27],"appearance":[28,81],"descriptors":[29,82],"and":[30,46],"lo-calizing":[31],"discriminative":[32],"parts.":[33],"To":[34],"this":[35],"end,":[36],"we":[37],"propose":[38],"an":[39,122],"object":[40],"representation":[41],"that":[42,64,116],"detects":[43],"important":[44],"parts":[45],"describes":[47],"appearances.":[49],"The":[50,80],"part":[51,102],"detectors":[52],"are":[53,83],"learned":[54,84],"in":[55,76],"a":[56,86],"fully":[57],"unsupervised":[58],"manner,":[59],"based":[60],"insight":[63],"images":[65],"with":[66],"similar":[67],"poses":[68],"can":[69],"be":[70,109],"automatically":[71],"discovered":[72],"for":[73,125],"classes":[75],"same":[78],"domain.":[79],"using":[85],"convolutional":[87],"neural":[88],"network.":[89],"Our":[90],"approach":[91],"requires":[92],"only":[93],"image":[94],"level":[95],"class":[96],"labels,":[97],"without":[98],"any":[99],"use":[100],"annotations":[103],"segmentation":[105],"masks,":[106],"which":[107],"may":[108],"costly":[110],"to":[111],"obtain.":[112],"show":[114],"experimentally":[115],"combining":[117],"these":[118],"insights":[120],"is":[121],"effective":[123],"strategy":[124],"recognition.":[127],"I.":[128]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-10-27T00:00:00"}