{"id":"https://openalex.org/W2527643446","doi":"https://doi.org/10.1145/2964284.2967205","title":"Learning to Make Better Mistakes","display_name":"Learning to Make Better Mistakes","publication_year":2016,"publication_date":"2016-09-29","ids":{"openalex":"https://openalex.org/W2527643446","doi":"https://doi.org/10.1145/2964284.2967205","mag":"2527643446"},"language":"en","primary_location":{"id":"doi:10.1145/2964284.2967205","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2967205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5101413394","display_name":"Hui Wu","orcid":"https://orcid.org/0000-0002-1742-5596"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Wu","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068061267","display_name":"Michele Merler","orcid":"https://orcid.org/0000-0002-4358-8671"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michele Merler","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065806033","display_name":"Rosario Uceda\u2010Sosa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rosario Uceda-Sosa","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110276035","display_name":"John R. Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Smith","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1005,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.86685569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"172","last_page":"176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10866","display_name":"Nutritional Studies and Diet","score":0.9714999794960022,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11584","display_name":"Biochemical Analysis and Sensing Techniques","score":0.9607999920845032,"subfield":{"id":"https://openalex.org/subfields/2916","display_name":"Nutrition and Dietetics"},"field":{"id":"https://openalex.org/fields/29","display_name":"Nursing"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8542655110359192},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6498633623123169},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6497985124588013},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.63717120885849},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6356940865516663},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6342316269874573},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6225003004074097},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5517411828041077},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5420286655426025},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.538689374923706},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5163046717643738},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5039135813713074},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35770511627197266},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0793621838092804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8542655110359192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6498633623123169},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6497985124588013},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.63717120885849},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6356940865516663},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6342316269874573},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6225003004074097},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5517411828041077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5420286655426025},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.538689374923706},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5163046717643738},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5039135813713074},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35770511627197266},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0793621838092804},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2964284.2967205","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2967205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W64813323","https://openalex.org/W1496513042","https://openalex.org/W1556540526","https://openalex.org/W1875842236","https://openalex.org/W1929903369","https://openalex.org/W1937922215","https://openalex.org/W2000105909","https://openalex.org/W2094931013","https://openalex.org/W2097117768","https://openalex.org/W2104265493","https://openalex.org/W2125269571","https://openalex.org/W2145541974","https://openalex.org/W2163969215","https://openalex.org/W2168371480","https://openalex.org/W2194011657","https://openalex.org/W2206370378","https://openalex.org/W2236282269","https://openalex.org/W2241525425","https://openalex.org/W2293499654","https://openalex.org/W2962685035","https://openalex.org/W2962860144","https://openalex.org/W2964189431","https://openalex.org/W3104226648","https://openalex.org/W3145063618"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W4323929292"],"abstract_inverted_index":{"We":[0,56],"propose":[1],"a":[2,23,30,43,61,68,88,93],"visual":[3],"food":[4,73,116],"recognition":[5],"framework":[6],"that":[7,120],"integrates":[8],"the":[9,39,52,98,104,107,111,121,130],"inherent":[10,112],"semantic":[11,54,113],"relationships":[12,114],"among":[13,115],"fine-grained":[14],"classes.":[15],"Our":[16],"method":[17,82],"learns":[18],"semantics-aware":[19],"features":[20],"by":[21],"formulating":[22],"multi-task":[24],"loss":[25],"function":[26],"on":[27,60,97],"top":[28],"of":[29,71,106,136],"convolutional":[31],"neural":[32],"network":[33,96],"(CNN)":[34],"architecture.":[35],"It":[36],"then":[37],"refines":[38],"CNN":[40],"predictions":[41],"using":[42],"random":[44],"walk":[45],"based":[46],"smoothing":[47],"procedure,":[48],"which":[49,90],"further":[50],"exploits":[51],"rich":[53],"information.":[55],"evaluate":[57],"our":[58],"algorithm":[59],"large":[62],"\"food-in-the-wild\"":[63],"benchmark,":[64],"as":[65,67],"well":[66],"challenging":[69],"dataset":[70],"restaurant":[72],"dishes":[74],"with":[75,110],"very":[76],"few":[77],"training":[78],"images.":[79],"The":[80],"proposed":[81,122],"achieves":[83],"higher":[84],"classification":[85],"accuracy":[86],"than":[87,129],"baseline":[89,131],"directly":[91],"fine-tunes":[92],"deep":[94],"learning":[95],"target":[99],"dataset.":[100],"Furthermore,":[101],"we":[102],"analyze":[103],"consistency":[105],"learned":[108],"model":[109],"categories.":[117],"Results":[118],"show":[119],"approach":[123],"provides":[124],"more":[125],"semantically":[126],"meaningful":[127],"results":[128],"method,":[132],"even":[133],"in":[134],"cases":[135],"mispredictions.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":7},{"year":2017,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}