{"id":"https://openalex.org/W7164939447","doi":"https://doi.org/10.1016/j.patcog.2026.114223","title":"Zero-shot referring expression comprehension via guidance of Multimodal Large Language Models","display_name":"Zero-shot referring expression comprehension via guidance of Multimodal Large Language Models","publication_year":2026,"publication_date":"2026-06-16","ids":{"openalex":"https://openalex.org/W7164939447","doi":"https://doi.org/10.1016/j.patcog.2026.114223"},"language":"en","primary_location":{"id":"doi:10.1016/j.patcog.2026.114223","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.114223","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","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/A5122784923","display_name":"Rouyi Li","orcid":null},"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"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rouyi Li","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","School of Artificial Intelligence, Shenzhen University, Shenzhen 518060, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"School of Artificial Intelligence, Shenzhen University, Shenzhen 518060, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138697003","display_name":"Wei Zhuo","orcid":null},"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"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhuo","raw_affiliation_strings":["National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, China","School of Artificial Intelligence, Shenzhen University, Shenzhen 518060, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"School of Artificial Intelligence, Shenzhen University, Shenzhen 518060, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027040096","display_name":"Shiyi Zheng","orcid":"https://orcid.org/0009-0004-0101-6597"},"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"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyi Zheng","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","School of Artificial Intelligence, Shenzhen University, Shenzhen 518060, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"School of Artificial Intelligence, Shenzhen University, Shenzhen 518060, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102002641","display_name":"Zhihao Wu","orcid":"https://orcid.org/0000-0002-2704-0614"},"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"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Wu","raw_affiliation_strings":["National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, China","School of Artificial Intelligence, Shenzhen University, Shenzhen 518060, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"School of Artificial Intelligence, Shenzhen University, Shenzhen 518060, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I3131625388"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019313200","display_name":"Linlin Shen","orcid":"https://orcid.org/0000-0003-1420-0815"},"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"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linlin Shen","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen 518060, China","School of Artificial Intelligence, Shenzhen University, Shenzhen 518060, China"],"raw_orcid":"https://orcid.org/0000-0003-1420-0815","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen 518060, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"School of Artificial Intelligence, Shenzhen University, Shenzhen 518060, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I3131625388"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019313200"],"corresponding_institution_ids":["https://openalex.org/I180726961","https://openalex.org/I3131625388"],"apc_list":{"value":2710,"currency":"USD","value_usd":2850},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75759276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"180","issue":null,"first_page":"114223","last_page":"114223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9681000113487244,"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":0.9681000113487244,"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":0.010300000198185444,"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":0.0019000000320374966,"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/comprehension","display_name":"Comprehension","score":0.7925999760627747},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.7038999795913696},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5812000036239624},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.460099995136261},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.32510000467300415},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.31279999017715454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8174999952316284},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.7925999760627747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7053999900817871},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.7038999795913696},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6593000292778015},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5812000036239624},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C2779679900","wikidata":"https://www.wikidata.org/wiki/Q25304431","display_name":"Saliency map","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2628999948501587}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.patcog.2026.114223","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.114223","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6336098909378052,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327098","display_name":"Guangdong Key Laboratory of Fermentation and Enzyme Engineering","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2779827764","https://openalex.org/W2896348597","https://openalex.org/W2947312908","https://openalex.org/W2962858109","https://openalex.org/W2963109634","https://openalex.org/W2964345792","https://openalex.org/W2966683369","https://openalex.org/W2986755220","https://openalex.org/W3006154882","https://openalex.org/W3112077297","https://openalex.org/W3126391825","https://openalex.org/W3216130706","https://openalex.org/W4221167437","https://openalex.org/W4385338579","https://openalex.org/W4385376328","https://openalex.org/W4386065691","https://openalex.org/W4386065874","https://openalex.org/W4386076148","https://openalex.org/W4388181804","https://openalex.org/W4391451889","https://openalex.org/W4393159049","https://openalex.org/W4394984751","https://openalex.org/W4396609326","https://openalex.org/W4400617758","https://openalex.org/W4401043359","https://openalex.org/W4402716383","https://openalex.org/W4403791857","https://openalex.org/W4409290320","https://openalex.org/W4414197327","https://openalex.org/W4416735359","https://openalex.org/W7133196460","https://openalex.org/W7160201759"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-06-17T00:00:00"}