{"id":"https://openalex.org/W4403791417","doi":"https://doi.org/10.1145/3664647.3681102","title":"A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal Reasoning","display_name":"A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal Reasoning","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791417","doi":"https://doi.org/10.1145/3664647.3681102"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681102","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5081759312","display_name":"Changmeng Zheng","orcid":"https://orcid.org/0000-0002-2945-8248"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Changmeng Zheng","raw_affiliation_strings":["The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dayong Liang","orcid":"https://orcid.org/0009-0004-0847-3416"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dayong Liang","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102635482","display_name":"Wengyu Zhang","orcid":"https://orcid.org/0009-0001-2347-4183"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wengyu Zhang","raw_affiliation_strings":["The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064374603","display_name":"Xiao-Yong Wei","orcid":"https://orcid.org/0000-0002-5706-5177"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiao-Yong Wei","raw_affiliation_strings":["The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100404176","display_name":"Qing Li","orcid":"https://orcid.org/0000-0003-3370-471X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5081759312"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.7312,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72649374,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"419","last_page":"428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9926999807357788,"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/T12031","display_name":"Speech and dialogue systems","score":0.9909999966621399,"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/blueprint","display_name":"Blueprint","score":0.8078866004943848},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6961695551872253},{"id":"https://openalex.org/keywords/paradigm-shift","display_name":"Paradigm shift","score":0.5686529874801636},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.519050657749176},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4223780632019043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33825066685676575},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2973599433898926},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1639454960823059},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.14450466632843018},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09942877292633057},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06307268142700195}],"concepts":[{"id":"https://openalex.org/C155911762","wikidata":"https://www.wikidata.org/wiki/Q422321","display_name":"Blueprint","level":2,"score":0.8078866004943848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6961695551872253},{"id":"https://openalex.org/C43540301","wikidata":"https://www.wikidata.org/wiki/Q689971","display_name":"Paradigm shift","level":2,"score":0.5686529874801636},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.519050657749176},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4223780632019043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33825066685676575},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2973599433898926},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1639454960823059},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.14450466632843018},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09942877292633057},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06307268142700195},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681102","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2075484438","https://openalex.org/W2560730294","https://openalex.org/W2593831809","https://openalex.org/W3092692431","https://openalex.org/W3104318719","https://openalex.org/W3183226462","https://openalex.org/W3207972321","https://openalex.org/W4212774754","https://openalex.org/W4221143046","https://openalex.org/W4296605665","https://openalex.org/W4319049530","https://openalex.org/W4323663038","https://openalex.org/W4367046983","https://openalex.org/W4389524566","https://openalex.org/W4390873421","https://openalex.org/W4392357044"],"related_works":["https://openalex.org/W4304620183","https://openalex.org/W2384575798","https://openalex.org/W2007211730","https://openalex.org/W2265189214","https://openalex.org/W2766654718","https://openalex.org/W2379378785","https://openalex.org/W4396600116","https://openalex.org/W1975337239","https://openalex.org/W1971312788","https://openalex.org/W4319347573"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,58,75],"pilot":[4],"study":[5,15],"aimed":[6],"at":[7,130],"introducing":[8],"multi-agent":[9],"debate":[10],"into":[11],"multimodal":[12],"reasoning.":[13],"The":[14,124],"addresses":[16],"two":[17],"key":[18],"challenges:":[19],"the":[20,29,44,54,92],"trivialization":[21,81],"of":[22,31,48],"opinions":[23],"resulting":[24],"from":[25,38,43],"excessive":[26],"summarization":[27],"and":[28,116],"diversion":[30],"focus":[32],"caused":[33,97],"by":[34,86,98],"distractor":[35],"concepts":[36],"introduced":[37],"images.":[39],"These":[40],"challenges":[41],"stem":[42],"inductive":[45],"(bottom-up)":[46],"nature":[47],"existing":[49],"debating":[50,61],"schemes.":[51],"To":[52],"address":[53],"issue,":[55],"we":[56],"propose":[57],"deductive":[59],"(top-down)":[60],"approach":[62],"called":[63],"Blueprint":[64],"Debate":[65],"on":[66],"Graphs":[67],"(BDoG).":[68],"In":[69],"BDoG,":[70],"debates":[71],"are":[72],"confined":[73],"to":[74,78,110],"blueprint":[76],"graph":[77],"prevent":[79],"opinion":[80],"through":[82],"world-level":[83],"summarization.":[84],"Moreover,":[85],"storing":[87],"evidence":[88],"in":[89,114],"branches":[90],"within":[91],"graph,":[93],"BDoG":[94,107],"mitigates":[95],"distractions":[96],"frequent":[99],"but":[100],"irrelevant":[101],"concepts.":[102],"Extensive":[103],"experiments":[104],"validate":[105],"that":[106],"is":[108],"able":[109],"achieve":[111],"state-of-the-art":[112],"results":[113],"ScienceQA":[115],"MMBench":[117],"with":[118],"significant":[119],"improvements":[120],"over":[121],"previous":[122],"methods.":[123],"source":[125],"code":[126],"can":[127],"be":[128],"accessed":[129],"https://github.com/thecharm/BDoG.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
