{"id":"https://openalex.org/W4403780493","doi":"https://doi.org/10.1145/3664647.3688990","title":"RAG-Guided Large Language Models for Visual Spatial Description with Adaptive Hallucination Corrector","display_name":"RAG-Guided Large Language Models for Visual Spatial Description with Adaptive Hallucination Corrector","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780493","doi":"https://doi.org/10.1145/3664647.3688990"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3688990","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3688990","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/A5048818071","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-3197-8103"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3197-8103","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090623425","display_name":"Yunxiang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunxiang Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-1980-7859","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046917338","display_name":"Zerui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zerui Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-1976-0889","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100546340","display_name":"Yang Zhao","orcid":"https://orcid.org/0009-0000-5169-3669"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Yang","raw_affiliation_strings":["Xi'an Jiaotong University, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0000-5169-3669","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Hefei, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079646718","display_name":"Gongpeng Zhao","orcid":"https://orcid.org/0009-0004-1019-1477"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongpeng Zhao","raw_affiliation_strings":["University of Science and Technology of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-1019-1477","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Beijing, China","institution_ids":["https://openalex.org/I92403157","https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109731559","display_name":"Fengzhao Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengzhao Sun","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0001-1164-0551","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084212167","display_name":"Fanrui Zhang","orcid":"https://orcid.org/0000-0002-1078-430X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fanrui Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1078-430X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115604895","display_name":"Qingsong Liu","orcid":"https://orcid.org/0009-0004-1208-3031"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingsong Liu","raw_affiliation_strings":["Unisound AI Technology Co., Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-1208-3031","affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047888605","display_name":"Jianqing Sun","orcid":"https://orcid.org/0009-0007-3598-8564"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianqing Sun","raw_affiliation_strings":["Unisound AI Technology Co., Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-3598-8564","affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039730743","display_name":"Jiaen Liang","orcid":"https://orcid.org/0009-0001-8309-1301"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaen Liang","raw_affiliation_strings":["Unisound AI Technology Co., Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-8309-1301","affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113162278","display_name":"Yaohui Zhang","orcid":"https://orcid.org/0009-0009-0147-5335"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaohui Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0009-0147-5335","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5311,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.84382003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11407","last_page":"11413"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9948999881744385,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9843999743461609,"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/computer-science","display_name":"Computer science","score":0.7146691083908081},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4696958065032959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4584881663322449},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32756203413009644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7146691083908081},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4696958065032959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4584881663322449},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32756203413009644}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3688990","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3688990","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1895989618","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W1947481528","https://openalex.org/W1965061793","https://openalex.org/W1980867644","https://openalex.org/W2041122820","https://openalex.org/W2051826382","https://openalex.org/W2251876105","https://openalex.org/W2277195237","https://openalex.org/W2767361967","https://openalex.org/W2901988662","https://openalex.org/W2963518342","https://openalex.org/W2963644680","https://openalex.org/W2964018924","https://openalex.org/W2964303913","https://openalex.org/W2975813532","https://openalex.org/W2976658881","https://openalex.org/W2981528363","https://openalex.org/W2981852735","https://openalex.org/W3027879771","https://openalex.org/W3199400376","https://openalex.org/W4288089799","https://openalex.org/W4381802186","https://openalex.org/W4402716288","https://openalex.org/W4402753774"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Visual":[0],"Spatial":[1],"Description":[2],"(VSD)":[3],"is":[4],"an":[5,22,47],"emerging":[6],"image-to-text":[7],"task":[8,42],"which":[9],"aims":[10],"at":[11],"generating":[12],"descriptions":[13],"of":[14,43],"the":[15,41,86],"spatial":[16,77],"relationships":[17],"between":[18],"given":[19],"objects":[20],"in":[21,33,75],"image.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27],"apply":[28],"Retrieval-Augmented":[29],"Generation":[30],"(RAG)":[31],"technology":[32],"guiding":[34],"Multimodal":[35],"Large":[36],"Language":[37],"Models":[38],"(MLLMs)":[39],"for":[40],"VSD,":[44],"complemented":[45],"by":[46],"Adaptive":[48],"Hallucination":[49],"Corrector,":[50],"and":[51,59,71,80],"further":[52],"fine-tuning":[53],"them":[54],"to":[55],"bolster":[56],"semantic":[57],"understanding":[58],"overall":[60],"model":[61],"efficacy.":[62],"We":[63],"found":[64],"that":[65],"our":[66],"approach":[67],"demonstrated":[68],"higher":[69],"accuracy":[70],"fewer":[72],"hallucination":[73],"errors":[74],"both":[76],"relationship":[78],"classification":[79],"visual":[81],"language":[82],"description":[83],"tasks":[84],"within":[85],"VSD":[87],"task,":[88],"achieving":[89],"state-of-the-art":[90],"results.":[91]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
