{"id":"https://openalex.org/W2949467366","doi":"https://doi.org/10.48550/arxiv.1603.08507","title":"Generating Visual Explanations","display_name":"Generating Visual Explanations","publication_year":2016,"publication_date":"2016-03-28","ids":{"openalex":"https://openalex.org/W2949467366","doi":"https://doi.org/10.48550/arxiv.1603.08507","mag":"2949467366"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1603.08507","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1603.08507","pdf_url":"https://arxiv.org/pdf/1603.08507","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1603.08507","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020758501","display_name":"Lisa Anne Hendricks","orcid":"https://orcid.org/0000-0001-9340-5143","observed_orcids":["https://orcid.org/0000-0001-9340-5143"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hendricks, Lisa Anne","raw_affiliation_strings":["UC Berkeley EECS , CA , United States","UC Berkeley, EECS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley EECS , CA , United States","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley, EECS","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040372929","display_name":"Zeynep Akata","orcid":"https://orcid.org/0000-0002-1432-7747","observed_orcids":["https://orcid.org/0000-0002-1432-7747"]},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Akata, Zeynep","raw_affiliation_strings":["Max Planck Institute for Informatics , Saarbr\u00fccken , Germany","Max Planck Institute for Informatics;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics , Saarbr\u00fccken , Germany","institution_ids":["https://openalex.org/I4210109712"]},{"raw_affiliation_string":"Max Planck Institute for Informatics;","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024481540","display_name":"Marcus Rohrbach","orcid":"https://orcid.org/0000-0001-5908-7751","observed_orcids":["https://orcid.org/0000-0001-5908-7751"]},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohrbach, Marcus","raw_affiliation_strings":["ICSI , Berkeley , CA , United States","UC Berkeley EECS , CA , United States","ICSI","UC Berkeley EECS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICSI , Berkeley , CA , United States","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"UC Berkeley EECS , CA , United States","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"ICSI","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"UC Berkeley EECS","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077819827","display_name":"Jeff Donahue","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donahue, Jeff","raw_affiliation_strings":["UC Berkeley EECS , CA , United States","UC Berkeley, EECS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley EECS , CA , United States","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley, EECS","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051534545","display_name":"Bernt Schiele","orcid":"https://orcid.org/0000-0001-9683-5237","observed_orcids":["https://orcid.org/0000-0001-9683-5237"]},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Schiele, Bernt","raw_affiliation_strings":["Max Planck Institute for Informatics , Saarbr\u00fccken , Germany","Max Planck Institute for Informatics;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics , Saarbr\u00fccken , Germany","institution_ids":["https://openalex.org/I4210109712"]},{"raw_affiliation_string":"Max Planck Institute for Informatics;","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533","observed_orcids":["https://orcid.org/0000-0001-5453-8533"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Darrell, Trevor","raw_affiliation_strings":["UC Berkeley EECS , CA , United States","UC Berkeley, EECS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley EECS , CA , United States","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley, EECS","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":88,"citation_normalized_percentile":null,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7310000061988831,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7310000061988831,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.26339998841285706,"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":0.003100000089034438,"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/explainable-classification","display_name":"explainable classification","score":0.5979999899864197},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7870000004768372},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.49399998784065247},{"id":"https://openalex.org/keywords/image-captioning","display_name":"image captioning","score":0.7269999980926514}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9073734283447266},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9062744379043579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7602866888046265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7227479815483093},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6701083779335022},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.6331143379211426},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6008776426315308},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5345228314399719},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.518837571144104},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5160946249961853},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.46884477138519287},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4361637234687805},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4273836612701416},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4100695252418518},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39499402046203613},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:1603.08507","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1603.08507","pdf_url":"https://arxiv.org/pdf/1603.08507","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"pmh:oai:escidoc.org:escidoc:2310184","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-002A-FCE5-9","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210088280","host_organization_name":"Max Planck Digital Library","host_organization_lineage":["https://openalex.org/I4210088280"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.mpg.de:item_2310184","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-002A-FCE5-9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Vision -- ECCV 2016","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.1603.08507","doi":"https://doi.org/10.48550/arxiv.1603.08507","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1603.08507","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1603.08507","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1603.08507","pdf_url":"https://arxiv.org/pdf/1603.08507","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1261808637","display_name":null,"funder_award_id":"N000141110688","funder_id":"https://openalex.org/F4320333591","funder_display_name":"Multidisciplinary University Research Initiative"},{"id":"https://openalex.org/G4771600513","display_name":"NRI: Collaborative Research: Shall I Touch This?: Navigating the Look and Feel of Complex Surfaces","funder_award_id":"1427425","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5641105978","display_name":"RI: Large: Collaborative Research: Reconstructive recognition: Uniting statistical scene understanding and physics-based visual reasoning","funder_award_id":"1212798","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6843723984","display_name":null,"funder_award_id":"N000141110688","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"},{"id":"https://openalex.org/F4320320875","display_name":"Deutscher Akademischer Austauschdienst","ror":"https://ror.org/039djdh30"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320333566","display_name":"National Defense Science and Engineering Graduate","ror":null},{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2949467366.pdf","grobid_xml":"https://content.openalex.org/works/W2949467366.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1797268635","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2055132753","https://openalex.org/W2101105183","https://openalex.org/W2102381086","https://openalex.org/W2107484060","https://openalex.org/W2108598243","https://openalex.org/W2119717200","https://openalex.org/W2123344105","https://openalex.org/W2129639577","https://openalex.org/W2130827850","https://openalex.org/W2139380585","https://openalex.org/W2142900973","https://openalex.org/W2155893237","https://openalex.org/W2159243025","https://openalex.org/W2171361956","https://openalex.org/W2173180041","https://openalex.org/W2220981600","https://openalex.org/W2292288263","https://openalex.org/W2953360861","https://openalex.org/W2963066927","https://openalex.org/W2963109634","https://openalex.org/W2963143606","https://openalex.org/W2963628945"],"related_works":["https://openalex.org/W2902869148","https://openalex.org/W2885386591","https://openalex.org/W3215769159","https://openalex.org/W7092317073","https://openalex.org/W2768835883","https://openalex.org/W4415687442","https://openalex.org/W2583695460","https://openalex.org/W3176080231","https://openalex.org/W2952061055","https://openalex.org/W3199693875"],"abstract_inverted_index":{"Clearly":[0],"explaining":[1],"a":[2,5,57,72,88,105,116],"rationale":[3],"for":[4,21,83],"classification":[6,120],"decision":[7,17],"to":[8,44,100,128],"an":[9,137],"end-user":[10],"can":[11,38],"be":[12],"as":[13,15,110],"important":[14],"the":[16,63,67,78,84],"itself.":[18],"Existing":[19],"approaches":[20],"deep":[22],"visual":[23,53],"recognition":[24],"are":[25,132],"generally":[26],"opaque":[27],"and":[28,75,95],"do":[29],"not":[30,133],"output":[31],"any":[32],"justification":[33],"text;":[34],"contemporary":[35],"vision-language":[36],"models":[37],"describe":[39],"image":[40,49,138],"content":[41],"but":[42,139],"fail":[43],"take":[45],"into":[46],"account":[47],"class-discriminative":[48],"aspects":[50],"which":[51,131],"justify":[52],"predictions.":[54],"We":[55,86],"propose":[56,87],"new":[58],"model":[59,125],"that":[60,98,103,123],"focuses":[61],"on":[62,93,115],"discriminating":[64],"properties":[65],"of":[66],"visible":[68],"object,":[69],"jointly":[70],"predicts":[71],"class":[73,111],"label,":[74],"explains":[76],"why":[77],"predicted":[79],"label":[80],"is":[81,126],"appropriate":[82],"image.":[85],"novel":[89],"loss":[90],"function":[91],"based":[92],"sampling":[94],"reinforcement":[96],"learning":[97],"learns":[99],"generate":[101,129],"sentences":[102],"realize":[104],"global":[106],"sentence":[107],"property,":[108],"such":[109],"specificity.":[112],"Our":[113],"results":[114],"fine-grained":[117],"bird":[118],"species":[119],"dataset":[121],"show":[122],"our":[124],"able":[127],"explanations":[130],"only":[134],"consistent":[135],"with":[136],"also":[140],"more":[141],"discriminative":[142],"than":[143],"descriptions":[144],"produced":[145],"by":[146],"existing":[147],"captioning":[148],"methods.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":19}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-06-27T00:00:00"}