{"id":"https://openalex.org/W4412888128","doi":"https://doi.org/10.18653/v1/2025.findings-acl.872","title":"MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering","display_name":"MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888128","doi":"https://doi.org/10.18653/v1/2025.findings-acl.872"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.872","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.872","pdf_url":"https://aclanthology.org/2025.findings-acl.872.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.872.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024712654","display_name":"Shuo Yang","orcid":"https://orcid.org/0000-0003-0190-3319"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuo Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110432703","display_name":"Cheon Goo Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caren Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078732700","display_name":"Siwen Luo","orcid":"https://orcid.org/0000-0003-0480-1991"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siwen Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060225743","display_name":"Eduard Hovy","orcid":"https://orcid.org/0000-0002-3270-7903"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eduard Hovy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16967","last_page":"16986"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9811000227928162,"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":0.9520999789237976,"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/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.8231388330459595},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.7850582599639893},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7483407855033875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.661894679069519},{"id":"https://openalex.org/keywords/magic","display_name":"MAGIC (telescope)","score":0.6274521946907043},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6088552474975586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49776485562324524},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45742854475975037},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.24693959951400757}],"concepts":[{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.8231388330459595},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.7850582599639893},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7483407855033875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.661894679069519},{"id":"https://openalex.org/C2777704519","wikidata":"https://www.wikidata.org/wiki/Q45732","display_name":"MAGIC (telescope)","level":2,"score":0.6274521946907043},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6088552474975586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49776485562324524},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45742854475975037},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.24693959951400757},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.872","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.872","pdf_url":"https://aclanthology.org/2025.findings-acl.872.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/f56d0d7d-14ad-4b7e-8583-9916b94c495d","is_oa":true,"landing_page_url":"https://admin.research-repository.uwa.edu.au/en/publications/f56d0d7d-14ad-4b7e-8583-9916b94c495d","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Yang, S, Han, S C, Luo, S & Hovy, E 2025, MAGIC-VQA : Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering. in W Che, J Nabende, E Shutova & M T Pilehvar (eds), Findings of the Association for Computational Linguistics : ACL 2025. Proceedings of the Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics (ACL), pp. 16967-16986, 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), Vienna, Austria, 27/07/25. https://doi.org/10.18653/v1/2025.findings-acl.872","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.872","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.872","pdf_url":"https://aclanthology.org/2025.findings-acl.872.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888128.pdf","grobid_xml":"https://content.openalex.org/works/W4412888128.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3035583586","https://openalex.org/W4320165839","https://openalex.org/W2151799802","https://openalex.org/W2196562041","https://openalex.org/W4385488510","https://openalex.org/W2073302931","https://openalex.org/W3206107299","https://openalex.org/W3082691151","https://openalex.org/W4287633646","https://openalex.org/W4313191056"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"requires":[4],"reasoning":[5,121],"across":[6],"visual":[7],"and":[8,62],"textual":[9],"modalities,":[10],"yet":[11],"Large":[12],"Vision-Language":[13],"Models":[14],"(LVLMs)":[15],"often":[16],"lack":[17],"integrated":[18],"commonsense":[19,41,120],"knowledge,":[20],"limiting":[21],"their":[22],"robustness":[23],"in":[24,122],"real-world":[25],"scenarios.To":[26],"address":[27],"this,":[28],"we":[29],"introduce":[30],"MAGIC-VQA,":[31],"a":[32,46,68,91],"novel":[33],"framework":[34,111],"that":[35],"enhances":[36],"VQA":[37],"by":[38,94],"systematically":[39],"integrating":[40],"knowledge":[42,97],"with":[43,98],"LVLMs.MAGIC-VQA":[44,89],"employs":[45],"three-stage":[47],"process:":[48],"(1)":[49],"Explicit":[50],"Knowledge":[51,65],"Integration":[52],"from":[53],"external":[54],"sources,":[55],"(2)":[56],"By-Type":[57],"Post-Processing":[58],"for":[59,73,104],"contextual":[60],"refinement,":[61],"(3)":[63],"Implicit":[64],"Augmentation":[66],"using":[67],"Graph":[69],"Neural":[70],"Network":[71],"(GNN)":[72],"structured":[74,81],"reasoning.While":[75],"GNNs":[76],"bring":[77],"greater":[78],"depth":[79],"to":[80],"inference,":[82],"they":[83],"enable":[84],"superior":[85],"relational":[86],"inference":[87],"beyond":[88],"bridges":[90],"key":[92],"gap":[93],"unifying":[95],"commonsensse":[96],"LVLMdriven":[99],"reasoning,":[100],"eliminating":[101],"the":[102],"need":[103],"extensive":[105],"pre-training":[106],"or":[107],"complex":[108],"prompt":[109],"tuning.Our":[110],"achieves":[112],"state-of-the-art":[113],"performance":[114],"on":[115,127],"benchmark":[116],"datasets,":[117],"significantly":[118],"improving":[119],"VQA.Our":[123],"implementation":[124],"is":[125],"open-sourced":[126],"GitHub":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}