{"id":"https://openalex.org/W4415539988","doi":"https://doi.org/10.1145/3746027.3758277","title":"GEMeX-RMCoT: An Enhanced Med-VQA Dataset for Region-Aware Multimodal Chain-of-Thought Reasoning","display_name":"GEMeX-RMCoT: An Enhanced Med-VQA Dataset for Region-Aware Multimodal Chain-of-Thought Reasoning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539988","doi":"https://doi.org/10.1145/3746027.3758277"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3758277","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758277","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3758277","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100461632","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-2165-245X"},"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":"Bo Liu","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong S.A.R., China"],"raw_orcid":"https://orcid.org/0000-0002-2165-245X","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong S.A.R., China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiangyu Zhao","orcid":"https://orcid.org/0000-0002-4468-5529"},"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":"Xiangyu Zhao","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong S.A.R., China"],"raw_orcid":"https://orcid.org/0000-0002-4468-5529","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong S.A.R., China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015947934","display_name":"Along He","orcid":"https://orcid.org/0000-0003-1356-8757"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Along He","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1356-8757","affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101974384","display_name":"Yidi Chen","orcid":"https://orcid.org/0000-0001-6293-4624"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210089761","display_name":"West China Hospital of Sichuan University","ror":"https://ror.org/007mrxy13","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210089761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidi Chen","raw_affiliation_strings":["West China Hospital of Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-6293-4624","affiliations":[{"raw_affiliation_string":"West China Hospital of Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976","https://openalex.org/I4210089761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010970485","display_name":"Huazhu Fu","orcid":"https://orcid.org/0000-0002-9702-5524"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huazhu Fu","raw_affiliation_strings":["IHPC, Agency for Science, Technology and Research, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9702-5524","affiliations":[{"raw_affiliation_string":"IHPC, Agency for Science, Technology and Research, Singapore, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101981128","display_name":"Xiao-Ming Wu","orcid":"https://orcid.org/0000-0002-3130-0554"},"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-Ming Wu","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong S.A.R., China"],"raw_orcid":"https://orcid.org/0000-0002-3130-0554","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong S.A.R., China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100461632"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15479964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13213","last_page":"13220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9962000250816345,"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/T10028","display_name":"Topic Modeling","score":0.9962000250816345,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9904999732971191,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9901000261306763,"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/process","display_name":"Process (computing)","score":0.6306999921798706},{"id":"https://openalex.org/keywords/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.5680000185966492},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5612999796867371},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.49799999594688416},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4246000051498413},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4007999897003174},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.37400001287460327},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.34209999442100525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829999923706055},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6306999921798706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6051999926567078},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.5680000185966492},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5612999796867371},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.49799999594688416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46790000796318054},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4246000051498413},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.30000001192092896},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25940001010894775},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3758277","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758277","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.17939","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.17939","pdf_url":"https://arxiv.org/pdf/2506.17939","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1145/3746027.3758277","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758277","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W3164670515","https://openalex.org/W3165058054","https://openalex.org/W3203635737","https://openalex.org/W4385245495","https://openalex.org/W4387321091","https://openalex.org/W4402774103","https://openalex.org/W4413050402"],"related_works":[],"abstract_inverted_index":{"Medical":[0],"visual":[1,90],"question":[2],"answering":[3],"aims":[4],"to":[5,12,49,111],"support":[6],"clinical":[7],"decision-making":[8],"by":[9,79],"enabling":[10],"models":[11],"answer":[13,37,76],"natural":[14],"language":[15],"questions":[16],"based":[17],"on":[18],"medical":[19,94],"images.":[20],"While":[21],"recent":[22],"advances":[23],"in":[24,69],"multi-modal":[25],"learning":[26,110],"have":[27],"significantly":[28],"improved":[29],"performance,":[30],"current":[31],"methods":[32],"still":[33],"suffer":[34],"from":[35],"limited":[36],"reliability":[38],"and":[39,47,51,122,142],"poor":[40],"interpretability,":[41],"impairing":[42],"the":[43,71,93,115,118,136,140,145],"ability":[44],"of":[45,73,82,92,135,144],"clinicians":[46],"patients":[48],"understand":[50],"trust":[52],"model":[53],"outputs.":[54],"To":[55],"address":[56],"these":[57],"limitations,":[58],"this":[59],"work":[60],"first":[61],"proposes":[62],"a":[63,80,103],"Region-Aware":[64],"Multimodal":[65],"Chain-of-Thought":[66],"(RMCoT)":[67],"dataset,":[68],"which":[70],"process":[72,121],"producing":[74],"an":[75],"is":[77,149],"preceded":[78],"sequence":[81],"intermediate":[83],"reasoning":[84,120],"steps":[85],"that":[86],"explicitly":[87],"ground":[88],"relevant":[89],"regions":[91],"image,":[95],"thereby":[96],"providing":[97],"fine-grained":[98],"explainability.":[99],"Furthermore,":[100],"we":[101],"introduce":[102],"novel":[104],"verifiable":[105],"reward":[106],"mechanism":[107],"for":[108],"reinforcement":[109],"guide":[112],"post-training,":[113],"improving":[114],"alignment":[116],"between":[117],"model's":[119],"its":[123],"final":[124],"answer.":[125],"Remarkably,":[126],"our":[127],"method":[128],"achieves":[129],"comparable":[130],"performance":[131],"using":[132],"only":[133],"one-eighth":[134],"training":[137],"data,":[138],"demonstrating":[139],"efficiency":[141],"effectiveness":[143],"proposal.":[146],"The":[147],"dataset":[148],"available":[150],"at":[151],"https://www.med-vqa.com/GEMeX/.":[152]},"counts_by_year":[],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2025-10-25T00:00:00"}