{"id":"https://openalex.org/W4403791441","doi":"https://doi.org/10.1145/3664647.3681249","title":"Cantor: Inspiring Multimodal Chain-of-Thought of MLLM","display_name":"Cantor: Inspiring Multimodal Chain-of-Thought of MLLM","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791441","doi":"https://doi.org/10.1145/3664647.3681249"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681249","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/A5111140063","display_name":"Timin Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Timin Gao","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0003-4034-2865","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109924324","display_name":"Peixian Chen","orcid":"https://orcid.org/0009-0008-8015-5366"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peixian Chen","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-8015-5366","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026072498","display_name":"Mengdan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengdan Zhang","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-2911-5369","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014172220","display_name":"Chaoyou Fu","orcid":"https://orcid.org/0000-0002-0079-7668"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoyou Fu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University &amp; School of Intelligence Science and Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0079-7668","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University &amp; School of Intelligence Science and Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039883116","display_name":"Yunhang Shen","orcid":"https://orcid.org/0000-0002-3970-7519"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhang Shen","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3970-7519","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030121180","display_name":"Yan Zhang","orcid":"https://orcid.org/0000-0003-1642-0758"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhang","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0003-1642-0758","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033991031","display_name":"Shengchuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengchuan Zhang","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-0800-0609","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054226277","display_name":"Xiawu Zheng","orcid":"https://orcid.org/0000-0002-6855-5403"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiawu Zheng","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-6855-5403","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004402130","display_name":"Xing Sun","orcid":"https://orcid.org/0000-0001-8132-9083"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Sun","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8132-9083","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014628588","display_name":"Liujuan Cao","orcid":"https://orcid.org/0000-0002-7645-9606"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liujuan Cao","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-7645-9606","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0001-9163-2932","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5111140063"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":3.9187,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94394935,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9096","last_page":"9105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9868999719619751,"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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9868999719619751,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9850000143051147,"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":0.9846000075340271,"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/computer-science","display_name":"Computer science","score":0.5455167293548584},{"id":"https://openalex.org/keywords/chain","display_name":"Chain (unit)","score":0.5181344747543335},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3282400369644165},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3259463906288147},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2540853023529053},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0671413242816925}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5455167293548584},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.5181344747543335},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3282400369644165},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3259463906288147},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2540853023529053},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0671413242816925},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681249","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":[{"id":"https://metadata.un.org/sdg/8","score":0.46000000834465027,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2981852735","https://openalex.org/W3093194982","https://openalex.org/W3099655892","https://openalex.org/W3205808193","https://openalex.org/W4212774754","https://openalex.org/W4224308101","https://openalex.org/W4226278401","https://openalex.org/W4281930370","https://openalex.org/W4288089799","https://openalex.org/W4318954855","https://openalex.org/W4386869711","https://openalex.org/W4387994822","https://openalex.org/W4393158343","https://openalex.org/W4393160064","https://openalex.org/W4393160302","https://openalex.org/W4393161084","https://openalex.org/W4402702887","https://openalex.org/W6810081322","https://openalex.org/W6812380799"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"With":[0],"the":[1,9,12,34,37,50,87,137,146,152,168,176,179],"advent":[2],"of":[3,36,52,89,156,178],"large":[4,100],"language":[5,101],"models(LLMs)":[6],"enhanced":[7],"by":[8,120],"chain-of-thought(CoT)":[10],"methodology,":[11],"visual":[13,47,70,80,95,133,192],"reasoning":[14,75,81,96,193],"problem":[15],"is":[16,76],"usually":[17],"decomposed":[18],"into":[19,86],"manageable":[20],"sub-tasks":[21],"and":[22,49,73,103,131,139],"tackled":[23],"sequentially":[24],"with":[25,98,145],"various":[26],"external":[27],"tools.":[28],"However,":[29],"such":[30],"a":[31,121,128,142],"paradigm":[32],"faces":[33],"challenge":[35],"potential":[38],"\"determining":[39],"hallucinations\"":[40],"in":[41,185],"decision":[42,129],"generation":[43,170],"due":[44],"to":[45,58,92,135,158],"insufficient":[46],"information":[48],"limitation":[51],"low-level":[53],"perception":[54],"tools":[55],"that":[56,68],"fail":[57],"provide":[59],"abstract":[60],"summaries":[61],"necessary":[62],"for":[63,78,163],"comprehensive":[64],"reasoning.":[65],"We":[66],"argue":[67],"converging":[69],"context":[71],"acquisition":[72],"logical":[74],"pivotal":[77],"tackling":[79],"tasks.":[82],"This":[83],"paper":[84],"delves":[85],"realm":[88],"multimodal":[90,99,114,186],"CoT":[91,115,169,187],"solve":[93],"intricate":[94],"tasks":[97],"models(MLLMs)":[102],"their":[104],"cognitive":[105,154],"capability.":[106],"To":[107],"this":[108],"end,":[109],"we":[110],"propose":[111],"an":[112],"innovative":[113],"framework,":[116,181],"termed":[117],"Cantor,":[118],"characterized":[119],"perception-decision":[122],"architecture.":[123],"Cantor":[124,150],"first":[125],"acts":[126],"as":[127,160],"generator":[130],"integrates":[132],"inputs":[134],"analyze":[136],"image":[138],"problem,":[140],"ensuring":[141],"closer":[143],"alignment":[144],"actual":[147],"context.":[148],"Furthermore,":[149],"leverages":[151],"advanced":[153],"functions":[155],"MLLMs":[157],"perform":[159],"multifaceted":[161],"experts":[162],"deriving":[164],"higher-level":[165],"information,":[166],"enhancing":[167],"process.":[171],"Our":[172],"extensive":[173],"experiments":[174],"demonstrate":[175],"efficacy":[177],"proposed":[180],"showing":[182],"significant":[183],"improvements":[184],"performance":[188],"across":[189],"two":[190],"complex":[191],"datasets,":[194],"without":[195],"necessitating":[196],"fine-tuning":[197],"or":[198],"ground-truth":[199],"rationales.":[200],"Project":[201],"Page:":[202],"https://ggg0919.github.io/cantor/.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
