{"id":"https://openalex.org/W4416582626","doi":"https://doi.org/10.1109/mmul.2025.3635870","title":"Improving Scene Knowledge Referring Expression Comprehension With Large Language Models","display_name":"Improving Scene Knowledge Referring Expression Comprehension With Large Language Models","publication_year":2025,"publication_date":"2025-11-24","ids":{"openalex":"https://openalex.org/W4416582626","doi":"https://doi.org/10.1109/mmul.2025.3635870"},"language":null,"primary_location":{"id":"doi:10.1109/mmul.2025.3635870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2025.3635870","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 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":null,"display_name":"Ruifan Li","orcid":"https://orcid.org/0009-0001-3829-5452"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruifan Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China","School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-3829-5452","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068753064","display_name":"Mingcong Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingcong Lu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China","School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1709-2584","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102631475","display_name":"Pengyue Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyue Lin","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China","School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9935-4375","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101490809","display_name":"Zhihan Yu","orcid":"https://orcid.org/0009-0000-6411-9420"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihan Yu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China","School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-6411-9420","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039812471","display_name":"Zhanyu Ma","orcid":"https://orcid.org/0000-0003-2950-2488"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanyu Ma","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China","School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2950-2488","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34814043,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"1","first_page":"72","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8111000061035156,"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":0.8111000061035156,"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/T13629","display_name":"Text Readability and Simplification","score":0.057500001043081284,"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":0.025800000876188278,"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/leverage","display_name":"Leverage (statistics)","score":0.6740000247955322},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5892999768257141},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4537000060081482},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45100000500679016},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4260999858379364},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4043000042438507},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.382999986410141},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.33880001306533813},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.33149999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8823000192642212},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6740000247955322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6392999887466431},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5892999768257141},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4595000147819519},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45100000500679016},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33820000290870667},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26579999923706055},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmul.2025.3635870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2025.3635870","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 MultiMedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1141036430","display_name":null,"funder_award_id":"2025AI4S15","funder_id":"https://openalex.org/F4320321470","funder_display_name":"Beijing University of Posts and Telecommunications"},{"id":"https://openalex.org/G1239235756","display_name":null,"funder_award_id":"2023YFC3305902","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G172479822","display_name":null,"funder_award_id":"62225601","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8677236040","display_name":null,"funder_award_id":"U23B2052","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321470","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scene":[0,92],"Knowledge":[1,93],"Referring":[2],"Expression":[3],"Comprehension":[4],"(SK-REC)":[5],"is":[6],"an":[7,110],"emerging":[8],"multimedia":[9],"reasoning":[10,19],"task.":[11],"It":[12],"requires":[13],"the":[14,31,55,64,80,85,121,131,137,141,149],"model":[15],"to":[16,26,62,79,113,124],"perform":[17],"joint":[18],"over":[20],"referring":[21,86,103],"expressions":[22,104],"and":[23,36,75,105,108,128,148],"scene":[24,34,66,106,126],"knowledge":[25,35,107,127],"locate":[27],"target":[28,81],"objects.":[29],"However,":[30],"complexity":[32],"of":[33,58,143],"redundant":[37],"information":[38],"could":[39],"cause":[40],"interference":[41],"with":[42],"models.":[43],"To":[44],"this":[45],"end,":[46],"we":[47,69,89],"propose":[48,90],"a":[49,91],"data":[50,145],"simplification":[51,146],"scheme.":[52],"We":[53],"leverage":[54],"understanding":[56],"capability":[57],"large":[59],"language":[60],"models":[61],"simplify":[63],"complex":[65],"knowledge.":[67],"Then,":[68],"can":[70],"filter":[71],"out":[72],"irrelevant":[73],"descriptions":[74],"keep":[76],"those":[77],"relevant":[78],"objects":[82],"involved":[83],"by":[84],"expression.":[87],"Furthermore,":[88],"Reasoning":[94],"Network":[95],"(SKRN).":[96],"Our":[97],"SKRN":[98],"extracts":[99],"features":[100],"from":[101],"both":[102],"employs":[109],"attention":[111],"mechanism":[112],"fully":[114],"utilize":[115],"them":[116],"for":[117],"reasoning.":[118],"This":[119],"enhances":[120],"model\u2019s":[122],"ability":[123],"handle":[125],"ultimately":[129],"improves":[130],"localization":[132],"accuracy.":[133],"Experimental":[134],"results":[135],"on":[136],"benchmark":[138],"dataset":[139],"demonstrate":[140],"effectiveness":[142],"our":[144],"scheme":[147],"proposed":[150],"SKRN.":[151]},"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-11-25T00:00:00"}