{"id":"https://openalex.org/W4298128025","doi":"https://doi.org/10.1109/ro-man53752.2022.9900586","title":"Improving Visual Question Answering by Leveraging Depth and Adapting Explainability","display_name":"Improving Visual Question Answering by Leveraging Depth and Adapting Explainability","publication_year":2022,"publication_date":"2022-08-29","ids":{"openalex":"https://openalex.org/W4298128025","doi":"https://doi.org/10.1109/ro-man53752.2022.9900586"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man53752.2022.9900586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man53752.2022.9900586","pdf_url":null,"source":{"id":"https://openalex.org/S4363607995","display_name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-310554","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010287647","display_name":"Amrita Panesar","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Amrita Panesar","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Robotics, Perception and Learning From the School of Electrical Engineering and Computer Science,Stockholm,Sweden","Division of Robotics, Perception and Learning From the School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning From the School of Electrical Engineering and Computer Science,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Robotics, Perception and Learning From the School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030295286","display_name":"Fethiye Irmak Do\u011fan","orcid":"https://orcid.org/0000-0002-1733-7019"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Fethiye Irmak Dogan","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Robotics, Perception and Learning From the School of Electrical Engineering and Computer Science,Stockholm,Sweden","Division of Robotics, Perception and Learning From the School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning From the School of Electrical Engineering and Computer Science,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Robotics, Perception and Learning From the School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082559019","display_name":"Iolanda Leite","orcid":"https://orcid.org/0000-0002-2212-4325"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Iolanda Leite","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Robotics, Perception and Learning From the School of Electrical Engineering and Computer Science,Stockholm,Sweden","Division of Robotics, Perception and Learning From the School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning From the School of Electrical Engineering and Computer Science,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Robotics, Perception and Learning From the School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.1849,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51441158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"252","last_page":"259"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9958999752998352,"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":0.9952999949455261,"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/leverage","display_name":"Leverage (statistics)","score":0.8214229941368103},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7787271738052368},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7687543630599976},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.7223489284515381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6656954288482666},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.639837384223938},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5859565734863281},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.581480860710144},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4859112799167633},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.44433847069740295},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4174291789531708},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3932810425758362},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35505393147468567}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8214229941368103},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7787271738052368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7687543630599976},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.7223489284515381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6656954288482666},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.639837384223938},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5859565734863281},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.581480860710144},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4859112799167633},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.44433847069740295},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4174291789531708},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3932810425758362},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35505393147468567},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ro-man53752.2022.9900586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man53752.2022.9900586","pdf_url":null,"source":{"id":"https://openalex.org/S4363607995","display_name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:kth-310554","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-310554","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bachelorThesis"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-310554","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-310554","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bachelorThesis"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1488163396","https://openalex.org/W1575833922","https://openalex.org/W1686810756","https://openalex.org/W1923184257","https://openalex.org/W1933349210","https://openalex.org/W2108598243","https://openalex.org/W2142192571","https://openalex.org/W2605409611","https://openalex.org/W2883171104","https://openalex.org/W2928096804","https://openalex.org/W2944850799","https://openalex.org/W2962858109","https://openalex.org/W2963890019","https://openalex.org/W2968124245","https://openalex.org/W2970355596","https://openalex.org/W2970526411","https://openalex.org/W2996325525","https://openalex.org/W3089935969","https://openalex.org/W3177561150","https://openalex.org/W3177947904","https://openalex.org/W4287080133","https://openalex.org/W4287081317","https://openalex.org/W4295312788","https://openalex.org/W4297783004","https://openalex.org/W4312562542","https://openalex.org/W6629203210","https://openalex.org/W6634232107","https://openalex.org/W6637373629","https://openalex.org/W6676297131","https://openalex.org/W6736518430","https://openalex.org/W6758719224","https://openalex.org/W6762157219","https://openalex.org/W6766978945","https://openalex.org/W6767279747","https://openalex.org/W6767455690","https://openalex.org/W6931870839"],"related_works":["https://openalex.org/W1968552888","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W2772323916","https://openalex.org/W1511346092","https://openalex.org/W1527532029","https://openalex.org/W2378167147","https://openalex.org/W3210777354","https://openalex.org/W2281307425","https://openalex.org/W2464405057"],"abstract_inverted_index":{"During":[0],"human-robot":[1],"conversation,":[2],"it":[3],"is":[4,31,163],"critical":[5],"for":[6,21,55,72],"robots":[7,39],"to":[8,11,65,111,126,134,153,169,176],"be":[9,62],"able":[10],"answer":[12,27],"users\u2019":[13],"questions":[14,46,109,142],"accurately":[15],"and":[16,121,143,172],"provide":[17,131],"a":[18,32,79],"suitable":[19],"explanation":[20],"why":[22],"they":[23,28],"arrive":[24],"at":[25],"the":[26,53,66,73,94,117,138,164],"provide.":[29],"Depth":[30],"crucial":[33],"component":[34],"in":[35,108],"producing":[36],"more":[37],"intelligent":[38],"that":[40,104,145],"can":[41],"respond":[42],"correctly":[43],"as":[44,114],"some":[45],"might":[47],"rely":[48],"on":[49,89,98,140,155],"spatial":[50],"relations":[51],"within":[52],"scene,":[54],"which":[56],"2D":[57],"RGB":[58,99,156],"data":[59,100],"alone":[60],"would":[61],"insufficient.":[63],"Due":[64],"lack":[67],"of":[68,75,119,124,166],"existing":[69],"depth":[70,112,171],"datasets":[71],"task":[74],"VQA,":[76],"we":[77,84,102],"introduce":[78],"new":[80],"dataset,":[81],"VQA-SUNRGBD.":[82],"When":[83],"compare":[85],"our":[86,146,159],"proposed":[87],"model":[88],"this":[90,161],"RGB-D":[91],"dataset":[92],"against":[93],"baseline":[95],"VQN":[96],"network":[97],"alone,":[101],"show":[103],"ours":[105],"outperforms,":[106],"particularly":[107],"relating":[110],"such":[113],"asking":[115],"about":[116],"proximity":[118],"objects":[120,125],"relative":[122],"positions":[123],"one":[127],"another.":[128],"We":[129],"also":[130],"Grad-CAM":[132,154],"activations":[133],"gain":[135],"insight":[136],"regarding":[137],"predictions":[139],"depth-related":[141],"find":[144],"method":[147],"produces":[148],"better":[149],"visual":[150],"explanations":[151],"compared":[152],"data.":[157],"To":[158],"knowledge,":[160],"work":[162],"first":[165],"its":[167],"kind":[168],"leverage":[170],"an":[173,178],"explainability":[174],"module":[175],"produce":[177],"explainable":[179],"Visual":[180],"Question":[181],"Answering":[182],"(VQA)":[183],"system.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}