{"id":"https://openalex.org/W2991027951","doi":"https://doi.org/10.1609/aaai.v34i07.6858","title":"Explanation vs Attention: A Two-Player Game to Obtain Attention for VQA","display_name":"Explanation vs Attention: A Two-Player Game to Obtain Attention for VQA","publication_year":2020,"publication_date":"2020-04-03","ids":{"openalex":"https://openalex.org/W2991027951","doi":"https://doi.org/10.1609/aaai.v34i07.6858","mag":"2991027951"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v34i07.6858","doi":"https://doi.org/10.1609/aaai.v34i07.6858","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v34i07.6858","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/6858/6712","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/6858/6712","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035714586","display_name":"Badri N. Patro","orcid":"https://orcid.org/0000-0002-2585-7014","observed_orcids":["https://orcid.org/0000-0002-2585-7014"]},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Badri Patro","raw_affiliation_strings":["Indian Institute of Technology","Indian Institute of Technology Kanpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology","institution_ids":[]},{"raw_affiliation_string":"Indian Institute of Technology Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028945877","display_name":"Anupriy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anupriy","raw_affiliation_strings":["Indian Institute of Technology","Indian Institute of Technology Kanpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology","institution_ids":[]},{"raw_affiliation_string":"Indian Institute of Technology Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007109424","display_name":"Vinay P. Namboodiri","orcid":"https://orcid.org/0000-0001-5262-9722","observed_orcids":["https://orcid.org/0000-0001-5262-9722"]},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinay Namboodiri","raw_affiliation_strings":["Indian Institute of Technology","Indian Institute of Technology Kanpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology","institution_ids":[]},{"raw_affiliation_string":"Indian Institute of Technology Kanpur","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94234084"],"apc_list":null,"apc_paid":null,"fwci":0.074,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.25387315,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":"34","issue":"07","first_page":"11848","last_page":"11855"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9214000105857849,"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":0.9214000105857849,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.06880000233650208,"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":0.003800000064074993,"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/visual-question-answering","display_name":"visual question answering","score":0.9990000128746033},{"id":"https://openalex.org/keywords/attention-maps","display_name":"attention maps","score":0.9200000166893005},{"id":"https://openalex.org/keywords/grad-cam","display_name":"Grad-CAM","score":0.8320000171661377},{"id":"https://openalex.org/keywords/visual-explanations","display_name":"visual explanations","score":0.878000020980835},{"id":"https://openalex.org/keywords/adversarial-training","display_name":"adversarial training","score":0.7749999761581421},{"id":"https://openalex.org/keywords/discriminator","display_name":"discriminator","score":0.6439999938011169},{"id":"https://openalex.org/keywords/distribution-alignment","display_name":"distribution alignment","score":0.5860000252723694},{"id":"https://openalex.org/keywords/human-attention","display_name":"human attention","score":0.6029999852180481},{"id":"https://openalex.org/keywords/correlation-alignment","display_name":"correlation alignment","score":0.45899999141693115},{"id":"https://openalex.org/keywords/maximum-mean-discrepancy","display_name":"maximum mean discrepancy","score":0.9509999752044678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7011803984642029},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.678521454334259},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6601586937904358},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6286380887031555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5400543808937073},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5216408371925354},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5034818053245544},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.48718637228012085},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.48668962717056274},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.4466512203216553},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44401639699935913},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.41738882660865784},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4147634208202362},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16649478673934937},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15862947702407837},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.10066401958465576},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v34i07.6858","doi":"https://doi.org/10.1609/aaai.v34i07.6858","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v34i07.6858","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/6858/6712","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1911.08618","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.08618","pdf_url":"https://arxiv.org/pdf/1911.08618","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":"mag:2991027951","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1911.08618.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1911.08618","doi":"https://doi.org/10.48550/arxiv.1911.08618","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.08618","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":"doi:10.1609/aaai.v34i07.6858","doi":"https://doi.org/10.1609/aaai.v34i07.6858","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v34i07.6858","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/6858/6712","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2991027951.pdf","grobid_xml":"https://content.openalex.org/works/W2991027951.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1510835000","https://openalex.org/W1514535095","https://openalex.org/W1565327149","https://openalex.org/W1575833922","https://openalex.org/W1895577753","https://openalex.org/W1895989618","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1933349210","https://openalex.org/W1965555277","https://openalex.org/W1983927101","https://openalex.org/W2056046632","https://openalex.org/W2067050450","https://openalex.org/W2105767494","https://openalex.org/W2149557440","https://openalex.org/W2151498684","https://openalex.org/W2179022885","https://openalex.org/W2293453011","https://openalex.org/W2424413254","https://openalex.org/W2463565445","https://openalex.org/W2532034655","https://openalex.org/W2553418567","https://openalex.org/W2560730294","https://openalex.org/W2563399268","https://openalex.org/W2581485081","https://openalex.org/W2593414223","https://openalex.org/W2603266952","https://openalex.org/W2616125804","https://openalex.org/W2745461083","https://openalex.org/W2787119853","https://openalex.org/W2795782778","https://openalex.org/W2804243936","https://openalex.org/W2809136100","https://openalex.org/W2889436406","https://openalex.org/W2894842749","https://openalex.org/W2934842096","https://openalex.org/W2950772592","https://openalex.org/W2962749469","https://openalex.org/W2962858109","https://openalex.org/W2963383024","https://openalex.org/W2963567641","https://openalex.org/W2963656855","https://openalex.org/W2963668159","https://openalex.org/W2963758027","https://openalex.org/W2963954913","https://openalex.org/W2964138017","https://openalex.org/W2964288524","https://openalex.org/W2967701591","https://openalex.org/W3000346474","https://openalex.org/W6680053761"],"related_works":["https://openalex.org/W4286751465","https://openalex.org/W3100786684","https://openalex.org/W4308236544","https://openalex.org/W2759653627","https://openalex.org/W2964312836","https://openalex.org/W4200335458","https://openalex.org/W2424413254","https://openalex.org/W2914694625","https://openalex.org/W3209226499","https://openalex.org/W2799846024"],"abstract_inverted_index":{"In":[0],"this":[1,251],"paper,":[2],"we":[3,26,83,131],"aim":[4],"to":[5,19,43,73,92,119,150],"obtain":[6],"improved":[7],"attention":[8,61,99,108,115,124,143,152,161,236,247],"for":[9,22,203],"a":[10,52,78,88,111,136,155,169],"visual":[11,30,96,127],"question":[12],"answering":[13],"(VQA)":[14],"task.":[15,179],"It":[16,165],"is":[17,28],"challenging":[18],"provide":[20,198],"supervision":[21,139],"attention.":[23],"An":[24],"observation":[25],"make":[27],"that":[29,40,64,90,133,145,225,246],"explanations":[31,128],"as":[32,57,77,110,207],"obtained":[33],"through":[34],"class":[35],"activation":[36],"mappings":[37],"(specifically":[38],"Grad-CAM)":[39],"are":[41,146],"meant":[42],"explain":[44],"the":[45,58,85,107,121,177,226,230,235,240],"performance":[46],"of":[47,54,60,65,80,87,95,103,106,123,138,233,239,253],"various":[48],"networks":[49],"could":[50],"form":[51,79,252],"means":[53,137,202],"supervision.":[55,81,254],"However,":[56],"distributions":[59,122,205],"maps":[62,125,144,248],"and":[63,98,116,126,191,217,223],"Grad-CAMs":[66],"differ,":[67],"it":[68],"would":[69],"not":[70],"be":[71,184],"suitable":[72],"directly":[74],"use":[75,86,102],"these":[76],"Rather,":[82],"propose":[84],"discriminator":[89],"aims":[91],"distinguish":[93],"samples":[94],"explanation":[97,117],"maps.":[100,237],"The":[101],"adversarial":[104,227],"training":[105],"regions":[109],"two-player":[112],"game":[113],"between":[114],"serves":[118],"bring":[120],"closer.":[129],"Significantly,":[130],"observe":[132,224],"providing":[134],"such":[135,206],"also":[140,166,183,197,242],"results":[141,167,192,241],"in":[142,154,168,172,193],"more":[147],"closely":[148],"related":[149],"human":[151],"resulting":[153],"substantial":[156],"improvement":[157,171],"over":[158],"baseline":[159],"stacked":[160],"network":[162],"(SAN)":[163],"models.":[164],"good":[170],"rank":[173],"correlation":[174],"metric":[175],"on":[176,209],"VQA":[178],"This":[180],"method":[181],"can":[182],"combined":[185],"with":[186,200],"recent":[187],"MCB":[188],"based":[189,208],"methods":[190],"consistent":[194],"improvement.":[195],"We":[196],"comparisons":[199],"other":[201,231],"learning":[204,234],"Correlation":[210],"Alignment":[211],"(Coral),":[212],"Maximum":[213],"Mean":[214,218],"Discrepancy":[215],"(MMD)":[216],"Square":[219],"Error":[220],"(MSE)":[221],"losses":[222],"loss":[228],"outperforms":[229],"forms":[232],"Visualization":[238],"confirms":[243],"our":[244],"hypothesis":[245],"improve":[249],"using":[250]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-12-05T00:00:00"}