{"id":"https://openalex.org/W2973009097","doi":"https://doi.org/10.18653/v1/w19-4812","title":"Faithful Multimodal Explanation for Visual Question Answering","display_name":"Faithful Multimodal Explanation for Visual Question Answering","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2973009097","doi":"https://doi.org/10.18653/v1/w19-4812","mag":"2973009097"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-4812","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4812","pdf_url":"https://www.aclweb.org/anthology/W19-4812.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-4812.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101825497","display_name":"Jialin Wu","orcid":"https://orcid.org/0000-0003-4684-5212"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jialin Wu","raw_affiliation_strings":["Department of Computer Science University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008715111","display_name":"Raymond J. Mooney","orcid":"https://orcid.org/0000-0002-4504-0490"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raymond Mooney","raw_affiliation_strings":["Department of Computer Science University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":72,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"103","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9947999715805054,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9940000176429749,"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/question-answering","display_name":"Question answering","score":0.8746258020401001},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7556825876235962},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6387180089950562},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.520331621170044},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.4960545003414154},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.42469507455825806},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4224739372730255},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3850216865539551},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3691158890724182},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.33519741892814636},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32040125131607056}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8746258020401001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7556825876235962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6387180089950562},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.520331621170044},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.4960545003414154},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.42469507455825806},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4224739372730255},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3850216865539551},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3691158890724182},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33519741892814636},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32040125131607056},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w19-4812","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4812","pdf_url":"https://www.aclweb.org/anthology/W19-4812.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-4812","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4812","pdf_url":"https://www.aclweb.org/anthology/W19-4812.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"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/W2973009097.pdf","grobid_xml":"https://content.openalex.org/works/W2973009097.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1559169059","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2063978378","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2130369780","https://openalex.org/W2154652894","https://openalex.org/W2282821441","https://openalex.org/W2332488709","https://openalex.org/W2463565445","https://openalex.org/W2506483933","https://openalex.org/W2516809705","https://openalex.org/W2563399268","https://openalex.org/W2745461083","https://openalex.org/W2776207810","https://openalex.org/W2788527488","https://openalex.org/W2803367139","https://openalex.org/W2883512601","https://openalex.org/W2884093133","https://openalex.org/W2895230054","https://openalex.org/W2934842096","https://openalex.org/W2946299408","https://openalex.org/W2951025380","https://openalex.org/W2962858109","https://openalex.org/W2963383024","https://openalex.org/W2963609017","https://openalex.org/W2963749936","https://openalex.org/W2963921921","https://openalex.org/W2963954913","https://openalex.org/W2964121744","https://openalex.org/W2970548373"],"related_works":["https://openalex.org/W4312822655","https://openalex.org/W3157170264","https://openalex.org/W4377865163","https://openalex.org/W4312601715","https://openalex.org/W4298185893","https://openalex.org/W2896078964","https://openalex.org/W4281399026","https://openalex.org/W2964061310","https://openalex.org/W2897842727","https://openalex.org/W2231285690"],"abstract_inverted_index":{"AI":[0],"systems'":[1],"ability":[2],"to":[3,9,49,94],"explain":[4],"their":[5,10],"reasoning":[6,74],"is":[7],"critical":[8],"utility":[11],"and":[12,63,101],"trustworthiness.":[13],"Deep":[14],"neural":[15],"networks":[16],"have":[17],"enabled":[18],"significant":[19],"progress":[20],"on":[21],"many":[22],"challenging":[23],"problems":[24],"such":[25],"as":[26],"visual":[27,64],"question":[28],"answering":[29],"(VQA).":[30],"However,":[31],"most":[32],"of":[33,71,80,90],"them":[34],"are":[35],"opaque":[36],"black":[37],"boxes":[38],"with":[39,60],"limited":[40],"explanatory":[41],"capability.":[42],"This":[43],"paper":[44],"presents":[45],"a":[46,51],"novel":[47],"approach":[48,92],"developing":[50],"high-performing":[52],"VQA":[53],"system":[54],"that":[55,66],"can":[56],"elucidate":[57],"its":[58,72],"answers":[59],"integrated":[61],"textual":[62],"explanations":[65],"faithfully":[67],"reflect":[68],"important":[69],"aspects":[70],"underlying":[73],"process":[75],"while":[76],"capturing":[77],"the":[78,88],"style":[79],"comprehensible":[81],"human":[82,102],"explanations.":[83],"Extensive":[84],"experimental":[85],"evaluation":[86],"demonstrates":[87],"advantages":[89],"this":[91],"compared":[93],"competing":[95],"methods":[96],"using":[97],"both":[98],"automated":[99],"metrics":[100],"evaluation.":[103]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}