{"id":"https://openalex.org/W4386590529","doi":"https://doi.org/10.1109/icip49359.2023.10223156","title":"Interpretable Visual Question Answering Via Reasoning Supervision","display_name":"Interpretable Visual Question Answering Via Reasoning Supervision","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386590529","doi":"https://doi.org/10.1109/icip49359.2023.10223156"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10223156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10223156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","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/A5068799758","display_name":"Maria Parelli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maria Parelli","raw_affiliation_strings":["DeepLab,Athens,Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepLab,Athens,Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051495888","display_name":"Dimitrios Mallis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitrios Mallis","raw_affiliation_strings":["DeepLab,Athens,Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepLab,Athens,Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089189446","display_name":"Markos Diomataris","orcid":"https://orcid.org/0000-0002-1112-0193"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Markos Diomataris","raw_affiliation_strings":["DeepLab,Athens,Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepLab,Athens,Greece","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040922549","display_name":"Vassilis Pitsikalis","orcid":"https://orcid.org/0000-0002-1593-7491"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vassilis Pitsikalis","raw_affiliation_strings":["DeepLab,Athens,Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepLab,Athens,Greece","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4254,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.62433207,"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":"2525","last_page":"2529"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9977999925613403,"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":0.9857000112533569,"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/question-answering","display_name":"Question answering","score":0.8281571269035339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6864722967147827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4831227958202362},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4273979067802429},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39107343554496765}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8281571269035339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6864722967147827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4831227958202362},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4273979067802429},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39107343554496765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10223156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10223156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2277195237","https://openalex.org/W2560730294","https://openalex.org/W2759653627","https://openalex.org/W2887978863","https://openalex.org/W2896457183","https://openalex.org/W2963115613","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2983256121","https://openalex.org/W3034854924","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3104788521","https://openalex.org/W3120237956","https://openalex.org/W3174690404","https://openalex.org/W3201957104","https://openalex.org/W4287125738","https://openalex.org/W4312331087","https://openalex.org/W4312341105","https://openalex.org/W4385574019","https://openalex.org/W6730531838","https://openalex.org/W6755207826","https://openalex.org/W6767211374","https://openalex.org/W6788554130","https://openalex.org/W6797109355","https://openalex.org/W6797756780"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3204019825","https://openalex.org/W2964061310","https://openalex.org/W2963477107","https://openalex.org/W2231285690","https://openalex.org/W3093385053","https://openalex.org/W4389682534","https://openalex.org/W4390091918","https://openalex.org/W3045060014","https://openalex.org/W4390241396"],"abstract_inverted_index":{"Transformer-based":[0],"architectures":[1],"have":[2],"recently":[3],"demonstrated":[4],"remarkable":[5],"performance":[6,153],"in":[7],"the":[8,34,39,79,86,113,121,127,130,140,145],"Visual":[9,97],"Question":[10],"Answering":[11],"(VQA)":[12],"task.":[13],"However,":[14],"such":[15,90],"models":[16],"are":[17],"likely":[18],"to":[19,37,46,152],"disregard":[20],"crucial":[21],"visual":[22,50,64,105,147],"cues":[23],"and":[24,30,129,137,150],"often":[25],"rely":[26],"on":[27,95,158],"multimodal":[28],"shortcuts":[29],"inherent":[31],"biases":[32],"of":[33,49,81,85,112],"language":[35],"modality":[36],"predict":[38],"correct":[40,87,131],"answer,":[41,88],"a":[42,60,73,82,116],"phenomenon":[43],"commonly":[44],"referred":[45],"as":[47,72],"lack":[48],"grounding.":[51],"In":[52],"this":[53,57],"work,":[54],"we":[55],"alleviate":[56],"shortcoming":[58],"through":[59,115],"novel":[61],"architecture":[62],"for":[63],"question":[65,128],"answering":[66],"that":[67,119,139],"leverages":[68],"common":[69],"sense":[70],"reasoning":[71],"supervisory":[74],"signal.":[75],"Reasoning":[76,100],"supervision":[77],"takes":[78],"form":[80],"textual":[83],"justification":[84],"with":[89],"annotations":[91],"being":[92],"already":[93],"available":[94],"large-scale":[96],"Common":[98],"Sense":[99],"(VCR)":[101],"datasets.":[102],"The":[103],"model\u2019s":[104,146],"attention":[106,123],"is":[107],"guided":[108,125],"toward":[109],"important":[110],"elements":[111],"scene":[114],"similarity":[117],"loss":[118],"aligns":[120],"learned":[122],"distributions":[124],"by":[126],"reasoning.":[132],"We":[133],"demonstrate":[134],"both":[135],"quantitatively":[136],"qualitatively":[138],"proposed":[141],"approach":[142],"can":[143],"boost":[144],"perception":[148],"capability":[149],"lead":[151],"increase,":[154],"without":[155],"requiring":[156],"training":[157],"explicit":[159],"grounding":[160],"annotations.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}