{"id":"https://openalex.org/W4408251899","doi":"https://doi.org/10.1109/tmm.2025.3543062","title":"Error-Aware Generative Reasoning for Zero-Shot Visual Grounding","display_name":"Error-Aware Generative Reasoning for Zero-Shot Visual Grounding","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408251899","doi":"https://doi.org/10.1109/tmm.2025.3543062"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3543062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3543062","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5045310029","display_name":"Yuqi Bu","orcid":"https://orcid.org/0000-0002-2158-8750"},"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":true,"raw_author_name":"Yuqi Bu","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101496006","display_name":"Xin Wu","orcid":"https://orcid.org/0000-0002-0207-0278"},"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":"Xin Wu","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089123257","display_name":"Yi Cai","orcid":"https://orcid.org/0000-0002-1767-789X"},"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":"Yi Cai","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100336310","display_name":"Qiong Liu","orcid":"https://orcid.org/0000-0002-6410-615X"},"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":"Qiong Liu","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453458","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0002-0437-0557"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tao Wang","raw_affiliation_strings":["Department of Biostatistics and Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Biostatistics and Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, U.K","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061381102","display_name":"Qingbao Huang","orcid":"https://orcid.org/0000-0001-7691-347X"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingbao Huang","raw_affiliation_strings":["School of Artificial Intelligence, Guangxi University, Nanning, China","School of Electrical Engineering, Institute of Artificial Intelligence, Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]},{"raw_affiliation_string":"School of Electrical Engineering, Institute of Artificial Intelligence, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5045310029"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76580575,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"4844","last_page":"4855"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9988999962806702,"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":0.8366919755935669},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5466920733451843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.528678834438324},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.49674636125564575},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4470347464084625},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39902400970458984},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3233450651168823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8366919755935669},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5466920733451843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.528678834438324},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.49674636125564575},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4470347464084625},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39902400970458984},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3233450651168823},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2025.3543062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3543062","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/d3378f90-fb96-4a71-ad3f-ab70b4df962a","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/d3378f90-fb96-4a71-ad3f-ab70b4df962a","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bu, Y, Wu, X, Cai, Y, Liu, Q, Wang, T & Huang, Q 2025, 'Error-Aware Generative Reasoning for Zero-Shot Visual Grounding', IEEE TRANSACTIONS ON MULTIMEDIA, vol. 27, pp. 4844 - 4855. https://doi.org/10.1109/TMM.2025.3543062","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G453967609","display_name":null,"funder_award_id":"62476097","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6770297356","display_name":null,"funder_award_id":"62276072","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8189774080","display_name":null,"funder_award_id":"62076100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8274614641","display_name":null,"funder_award_id":"x2rjD2240100","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8718620462","display_name":null,"funder_award_id":"2020B0101100002","funder_id":"https://openalex.org/F4320335795","funder_display_name":"Science and Technology Planning Project of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320313345","display_name":"Maudsley Charity","ror":"https://ror.org/028vg3q27"},{"id":"https://openalex.org/F4320319990","display_name":"National Institute for Health and Care Research","ror":"https://ror.org/0187kwz08"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320335795","display_name":"Science and Technology Planning Project of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2489434015","https://openalex.org/W2724492314","https://openalex.org/W2745461083","https://openalex.org/W2792265253","https://openalex.org/W2935033494","https://openalex.org/W2955639361","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2983693499","https://openalex.org/W2990803704","https://openalex.org/W2997063389","https://openalex.org/W3034359780","https://openalex.org/W3034578524","https://openalex.org/W3035097537","https://openalex.org/W3039232647","https://openalex.org/W3049293589","https://openalex.org/W3081167590","https://openalex.org/W3090072755","https://openalex.org/W3090449556","https://openalex.org/W3099554308","https://openalex.org/W3102363003","https://openalex.org/W3106029750","https://openalex.org/W3109060525","https://openalex.org/W3112077297","https://openalex.org/W3130619535","https://openalex.org/W3159619744","https://openalex.org/W3159637683","https://openalex.org/W3169884222","https://openalex.org/W3173220247","https://openalex.org/W3174004334","https://openalex.org/W3179041377","https://openalex.org/W3199693760","https://openalex.org/W3200763177","https://openalex.org/W3205869909","https://openalex.org/W3214910576","https://openalex.org/W4205542840","https://openalex.org/W4214490042","https://openalex.org/W4220771488","https://openalex.org/W4220869836","https://openalex.org/W4224308101","https://openalex.org/W4225517085","https://openalex.org/W4283026156","https://openalex.org/W4285192809","https://openalex.org/W4285787895","https://openalex.org/W4289639375","https://openalex.org/W4295046616","https://openalex.org/W4312456860","https://openalex.org/W4312956471","https://openalex.org/W4313145013","https://openalex.org/W4313184803","https://openalex.org/W4322754188","https://openalex.org/W4353113046","https://openalex.org/W4385194708","https://openalex.org/W4385893917","https://openalex.org/W4386065691","https://openalex.org/W4386076148","https://openalex.org/W4389523957","https://openalex.org/W4390872747","https://openalex.org/W4390874575","https://openalex.org/W4391451889","https://openalex.org/W4392669753","https://openalex.org/W4394828156","https://openalex.org/W4399557965"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W4411535265","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2051487156","https://openalex.org/W2359774528"],"abstract_inverted_index":{"Zero-shot":[0],"visual":[1,31,34,70,86,102,142],"grounding":[2],"is":[3,116,151],"the":[4,106,134],"task":[5],"of":[6,73,109,145,183],"identifying":[7,67],"and":[8,68,160,180],"localizing":[9],"an":[10,13,94,148,181],"object":[11],"in":[12,77],"image":[14],"based":[15,83],"on":[16,84,136,166],"a":[17,47,64,112],"referring":[18,128],"expression":[19],"without":[20],"task-specific":[21],"training.":[22],"Existing":[23],"methods":[24,62,175],"employ":[25],"heuristic":[26,138],"rules":[27],"to":[28,121,153,156,178],"step-by-step":[29],"perform":[30],"perception":[32,87],"for":[33,66,100,126],"grounding.":[35,103],"Despite":[36],"their":[37],"remarkable":[38],"performance,":[39],"there":[40],"are":[41,54],"still":[42],"two":[43],"limitations.":[44],"First,":[45],"such":[46],"rule-based":[48],"manner":[49,132],"struggles":[50],"with":[51],"expressions":[52],"that":[53,170],"not":[55],"covered":[56],"by":[57,81,176],"predefined":[58],"rules.":[59,139],"Second,":[60],"existing":[61,110],"lack":[63],"mechanism":[65,150],"correcting":[69],"perceptual":[71,143],"errors":[72,79,144,159],"incomplete":[74,85,146],"information,":[75,147],"resulting":[76],"cascading":[78],"caused":[80],"reasoning":[82,113,124],"results.":[88],"In":[89],"this":[90],"article,":[91],"we":[92],"propose":[93],"Error-Aware":[95],"Generative":[96],"Reasoning":[97],"(EAGR)":[98],"method":[99],"zero-shot":[101,174],"To":[104,140],"address":[105],"limited":[107],"adaptability":[108],"methods,":[111],"chain":[114],"generator":[115],"presented,":[117],"which":[118],"prompts":[119],"LLMs":[120,155],"dynamically":[122],"generate":[123],"chains":[125],"specific":[127],"expressions.":[129],"This":[130],"generative":[131],"eliminates":[133],"reliance":[135],"human-written":[137],"mitigate":[141],"error-aware":[149],"presented":[152],"elicit":[154],"identify":[157],"these":[158],"explore":[161],"correction":[162],"strategies.":[163],"Experimental":[164],"results":[165],"four":[167],"benchmarks":[168],"show":[169],"EAGR":[171],"outperforms":[172],"state-of-the-art":[173],"up":[177],"10%":[179],"average":[182],"7%.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}