{"id":"https://openalex.org/W4390478989","doi":"https://doi.org/10.1145/3595916.3626376","title":"From Pixels to Explanations: Uncovering the Reasoning Process in Visual Question Answering","display_name":"From Pixels to Explanations: Uncovering the Reasoning Process in Visual Question Answering","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4390478989","doi":"https://doi.org/10.1145/3595916.3626376"},"language":"en","primary_location":{"id":"doi:10.1145/3595916.3626376","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626376","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626376","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626376","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049835424","display_name":"S. Zhang","orcid":"https://orcid.org/0009-0001-3187-9332"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Siqi Zhang","raw_affiliation_strings":["Tongji University, CN"],"affiliations":[{"raw_affiliation_string":"Tongji University, CN","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108392430","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-0903-9131"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["National Lab of Pattern Recognition, Institute of Automation,Chinese Academy of Sciences, CN"],"affiliations":[{"raw_affiliation_string":"National Lab of Pattern Recognition, Institute of Automation,Chinese Academy of Sciences, CN","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004301353","display_name":"Zhihua Wei","orcid":"https://orcid.org/0000-0002-5937-3907"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihua Wei","raw_affiliation_strings":["Tongji University, CN"],"affiliations":[{"raw_affiliation_string":"Tongji University, CN","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049835424"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.178035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9896000027656555,"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":0.9855999946594238,"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/interpretability","display_name":"Interpretability","score":0.7848349809646606},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.7505248785018921},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7345081567764282},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.733431339263916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6472734212875366},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.604870617389679},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.550143837928772},{"id":"https://openalex.org/keywords/qualitative-reasoning","display_name":"Qualitative reasoning","score":0.5391782522201538},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5255162715911865},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.5239629745483398},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.47783827781677246},{"id":"https://openalex.org/keywords/deductive-reasoning","display_name":"Deductive reasoning","score":0.4625524878501892},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4597805142402649},{"id":"https://openalex.org/keywords/analogical-reasoning","display_name":"Analogical reasoning","score":0.4447616636753082},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.42893874645233154},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.3369109630584717},{"id":"https://openalex.org/keywords/analogy","display_name":"Analogy","score":0.15425392985343933},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07830837368965149},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07407832145690918}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7848349809646606},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.7505248785018921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7345081567764282},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.733431339263916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6472734212875366},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.604870617389679},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.550143837928772},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.5391782522201538},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5255162715911865},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.5239629745483398},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.47783827781677246},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.4625524878501892},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4597805142402649},{"id":"https://openalex.org/C2985612853","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogical reasoning","level":3,"score":0.4447616636753082},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.42893874645233154},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3369109630584717},{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.15425392985343933},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07830837368965149},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07407832145690918},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3595916.3626376","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626376","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626376","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3595916.3626376","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626376","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626376","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1283858192","display_name":null,"funder_award_id":"U21B2043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1614471940","display_name":null,"funder_award_id":"2020AAA0","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2244573216","display_name":null,"funder_award_id":"62206279","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G23458378","display_name":null,"funder_award_id":"61976160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5036809106","display_name":null,"funder_award_id":"62076182","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5387966317","display_name":null,"funder_award_id":"61906137","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5577970204","display_name":null,"funder_award_id":"2020AAA0106400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5686205310","display_name":null,"funder_award_id":"62076184","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7424057548","display_name":null,"funder_award_id":"No. 2020AAA0106400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8264781341","display_name":null,"funder_award_id":"61976158","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390478989.pdf","grobid_xml":"https://content.openalex.org/works/W4390478989.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2156050087","https://openalex.org/W2560674852","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2747329762","https://openalex.org/W2793546384","https://openalex.org/W2904910963","https://openalex.org/W2962716332","https://openalex.org/W2963115613","https://openalex.org/W2963518342","https://openalex.org/W2963609017","https://openalex.org/W2963644680","https://openalex.org/W2964118342","https://openalex.org/W2969679616","https://openalex.org/W2998631105","https://openalex.org/W3004227146","https://openalex.org/W3016923549","https://openalex.org/W3022458567","https://openalex.org/W3035497460","https://openalex.org/W3035517717","https://openalex.org/W3099849198","https://openalex.org/W3147260715","https://openalex.org/W3159619744","https://openalex.org/W3173220247","https://openalex.org/W3208314443","https://openalex.org/W4206908526"],"related_works":["https://openalex.org/W2347305376","https://openalex.org/W2349790191","https://openalex.org/W1816891706","https://openalex.org/W2392104753","https://openalex.org/W1540734423","https://openalex.org/W2148216026","https://openalex.org/W94330105","https://openalex.org/W1837960042","https://openalex.org/W2113245685","https://openalex.org/W161479560"],"abstract_inverted_index":{"Visual":[0],"reasoning":[1,7,25,62,73,84,103,134],"requires":[2],"models":[3],"to":[4,22,37,53,70,86,130,143],"construct":[5],"a":[6,59,66,120,127,145,160],"process":[8,46],"towards":[9],"the":[10,24,45,72,78,90,102,114,132,137,156,168,177],"final":[11,115],"decision.":[12],"Previous":[13],"studies":[14],"have":[15,29],"used":[16],"attention":[17],"maps":[18,33],"or":[19],"textual":[20,40],"explanations":[21,41],"illustrate":[23],"process,":[26],"but":[27],"both":[28,50],"their":[30],"limitations.":[31],"Attention":[32],"can":[34,140,151],"be":[35,141,152],"difficult":[36],"read,":[38],"while":[39],"cannot":[42],"fully":[43],"describe":[44],"of":[47],"reasoning,":[48],"and":[49,82,92,111,124,147,171],"are":[51,105],"hard":[52],"evaluate":[54],"quantitatively.":[55,154],"This":[56],"paper":[57],"proposes":[58],"novel":[60],"pixel-to-explanation":[61],"model":[63,76,166],"that":[64,150],"employs":[65],"user-friendly":[67],"multimodal":[68],"rationale":[69],"depict":[71],"process.":[74,135],"The":[75,98],"dissects":[77],"question":[79,93],"into":[80,107,126],"subquestions,":[81],"constructs":[83],"cells":[85,104],"retrieve":[87],"knowledge":[88],"from":[89,101],"image":[91],"based":[94],"on":[95,167,176],"these":[96],"subquestions.":[97],"intermediate":[99],"outcomes":[100],"translated":[106,125],"object":[108],"bounding":[109],"boxes":[110],"classes,":[112],"with":[113],"output":[116],"beging":[117],"classified":[118],"as":[119],"standard":[121],"VQA":[122],"answer":[123,129],"complete":[128],"summarize":[131],"entire":[133],"All":[136],"generated":[138],"results":[139,175],"combined":[142],"produce":[144],"human-readable":[146],"informative":[148],"explanation":[149],"evaluated":[153],"Besides":[155],"interpretability,":[157],"we":[158],"achieved":[159],"4.4%":[161],"improvement":[162],"over":[163],"our":[164],"baseline":[165],"GQA":[169],"dataset":[170],"attained":[172],"new":[173],"state-of-the-art":[174],"challenging":[178],"GQA-OOD":[179],"dataset.":[180]},"counts_by_year":[],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}