{"id":"https://openalex.org/W4417201535","doi":"https://doi.org/10.1109/tcsvt.2025.3642691","title":"Cyclic Pseudo-Label Generation and Refinement for Weakly Supervised Referring Expression Grounding","display_name":"Cyclic Pseudo-Label Generation and Refinement for Weakly Supervised Referring Expression Grounding","publication_year":2025,"publication_date":"2025-12-10","ids":{"openalex":"https://openalex.org/W4417201535","doi":"https://doi.org/10.1109/tcsvt.2025.3642691"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3642691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3642691","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5113335839","display_name":"Jiahe Wu","orcid":"https://orcid.org/0009-0003-1185-5848"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahe Wu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China","Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0003-1185-5848","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005367680","display_name":"Zhong Ji","orcid":"https://orcid.org/0000-0002-2197-3739"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Ji","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China","Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-2197-3739","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036870586","display_name":"Yaodong Wang","orcid":"https://orcid.org/0009-0008-8299-5844"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaodong Wang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China","Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0008-8299-5844","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086887025","display_name":"Yanwei Pang","orcid":"https://orcid.org/0000-0001-6670-3727"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Pang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China","Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-6670-3727","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046605531","display_name":"Jungong Han","orcid":"https://orcid.org/0000-0003-4361-956X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jungong Han","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4361-956X","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36289715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"5","first_page":"5839","last_page":"5851"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5981000065803528,"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":0.5981000065803528,"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":0.23029999434947968,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.032499998807907104,"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":0.6998999714851379},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5889000296592712},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5457000136375427},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44600000977516174},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4327999949455261},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.42890000343322754},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.42179998755455017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766700029373169},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6998999714851379},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5889000296592712},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5457000136375427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4772999882698059},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.42890000343322754},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.39590001106262207},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3882000148296356},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37439998984336853},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3149000108242035},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2892000079154968},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2630999982357025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3642691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3642691","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G338250432","display_name":null,"funder_award_id":"62441235","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3930161243","display_name":null,"funder_award_id":"62176178","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Weakly":[0],"supervised":[1,173],"Referring":[2],"Expression":[3],"Grounding":[4],"(WREG)":[5],"aims":[6],"at":[7,182],"grounding":[8],"the":[9,18,32,43,49,64,74,84,87,104,111,117,150,169],"target":[10],"region":[11,121],"based":[12],"on":[13,128,159],"a":[14,94,139],"given":[15],"expression,":[16],"where":[17],"mapping":[19],"between":[20],"regions":[21],"and":[22,98,154,177],"expressions":[23],"is":[24,80],"unknown":[25],"during":[26],"training.":[27],"Recent":[28],"WREG":[29,77],"methods":[30],"leverage":[31],"strategy":[33],"of":[34,76,86,113,119,152],"generating":[35],"pseudo-labels":[36,153],"utilizing":[37,144],"Vision-Language":[38],"Pre-training":[39],"(VLP)":[40],"to":[41,68,73,82,102,115,130,148],"avoid":[42],"cross-modal":[44,145],"heterogeneous":[45],"gaps":[46],"arising":[47],"from":[48],"two-stage":[50],"reconstruction":[51],"strategy.":[52],"However,":[53],"mainstream":[54],"VLPs":[55],"are":[56],"trained":[57],"with":[58,134],"image-text":[59],"alignment":[60],"data,":[61,78],"which":[62],"makes":[63],"generated":[65],"labels":[66],"inapplicable":[67],"REG":[69,125],"task.":[70],"Furthermore,":[71],"due":[72],"constraints":[75],"it":[79],"challenging":[81],"ensure":[83,155],"quality":[85],"pseudo-labels.":[88],"To":[89],"this":[90],"end,":[91],"we":[92,108,137],"propose":[93],"Cyclic":[95],"Pseudo-label":[96,140],"Generation":[97],"Refinement":[99,141],"(CPGR)":[100],"method":[101,167],"alleviate":[103,116],"above":[105],"limitations.":[106],"Specifically,":[107],"cycle":[109],"through":[110],"process":[112],"Generation-Refinement-Grounding":[114],"impact":[118],"missing":[120],"annotations.":[122],"We":[123],"perform":[124],"task-adaptive":[126],"fine-tuning":[127],"BLIP-2":[129],"generate":[131],"REG-style":[132],"descriptions":[133],"Region-Centrality.":[135],"Then,":[136],"design":[138],"module":[142],"by":[143],"token":[146],"attention":[147],"enhance":[149],"reliability":[151],"their":[156],"Reference-Discrimination.":[157],"Experiments":[158],"five":[160],"benchmark":[161],"datasets":[162],"demonstrate":[163],"that":[164],"our":[165],"proposed":[166],"outperforms":[168],"current":[170],"state-of-the-art":[171],"weakly":[172],"methods.":[174],"Our":[175],"code":[176],"models":[178],"will":[179],"be":[180],"released":[181],"https://github.com/5jiahe/CPGR.":[183]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2025-12-10T00:00:00"}