{"id":"https://openalex.org/W4416177748","doi":"https://doi.org/10.1109/tcsvt.2025.3632245","title":"GC <sup>3</sup> VG: Generalized Multi-Task Visual Grounding With Coarse-to-Fine Consistency Constraints","display_name":"GC <sup>3</sup> VG: Generalized Multi-Task Visual Grounding With Coarse-to-Fine Consistency Constraints","publication_year":2025,"publication_date":"2025-11-13","ids":{"openalex":"https://openalex.org/W4416177748","doi":"https://doi.org/10.1109/tcsvt.2025.3632245"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3632245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3632245","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/A5006968955","display_name":"Ming Jiang Dai","orcid":"https://orcid.org/0009-0004-6133-0035"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Dai","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0004-6133-0035","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kai Chen","orcid":"https://orcid.org/0009-0006-9053-3469"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-9053-3469","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074230503","display_name":"W. S. Cheng","orcid":"https://orcid.org/0009-0008-5915-9565"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxuan Cheng","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0008-5915-9565","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004604326","display_name":"Jiedong Zhuang","orcid":"https://orcid.org/0000-0003-0551-5911"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiedong Zhuang","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025299678","display_name":"Zhenhua Feng","orcid":"https://orcid.org/0000-0002-4485-4249"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Feng","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0002-4485-4249","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006952581","display_name":"Pengfei Zhu","orcid":"https://orcid.org/0000-0002-4310-9140"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Zhu","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-4310-9140","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100748706","display_name":"Wankou Yang","orcid":"https://orcid.org/0000-0002-6385-6776"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wankou Yang","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-6385-6776","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.30635433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"4","first_page":"4827","last_page":"4841"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9617000222206116,"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":0.9617000222206116,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.010099999606609344,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.005499999970197678,"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/generalizability-theory","display_name":"Generalizability theory","score":0.7555999755859375},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.748199999332428},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6248000264167786},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5756999850273132},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.46959999203681946},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4456999897956848},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4431999921798706},{"id":"https://openalex.org/keywords/local-consistency","display_name":"Local consistency","score":0.38989999890327454},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38960000872612}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.7555999755859375},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.748199999332428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6273000240325928},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6248000264167786},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5756999850273132},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.46959999203681946},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4643999934196472},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4456999897956848},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C137105694","wikidata":"https://www.wikidata.org/wiki/Q3407510","display_name":"Local consistency","level":4,"score":0.38989999890327454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.36730000376701355},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.36160001158714294},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.30480000376701355},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29829999804496765},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C175652121","wikidata":"https://www.wikidata.org/wiki/Q4379351","display_name":"Causal consistency","level":5,"score":0.26019999384880066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3632245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3632245","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/G7077580569","display_name":null,"funder_award_id":"62436002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G782967413","display_name":null,"funder_award_id":"62276061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8389771718","display_name":null,"funder_award_id":"CXJH SEU 25125","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":{"In":[0,59],"this":[1,77],"work,":[2],"we":[3,143],"propose":[4,144],"an":[5,190],"efficient":[6],"and":[7,32,40,52,100,110,124,165,180,193,210,218,225,230],"streamlined":[8],"paradigm":[9],"to":[10,36,55,119,128,159],"address":[11],"the":[12,50,65,95,106,207,213,228,233],"challenge":[13],"of":[14,69,97,216,232],"consistency":[15,102,205],"prediction":[16,204],"in":[17,206],"generalized":[18,160],"multi-task":[19,34,74,80],"visual":[20,39,81,121,217],"grounding.":[21],"While":[22],"most":[23],"existing":[24],"approaches":[25],"primarily":[26],"focus":[27],"on":[28,46,85,223],"integrating":[29],"multi-modal":[30],"information":[31],"employing":[33],"learning":[35],"enhance":[37],"both":[38,98,163],"linguistic":[41,219],"understanding,":[42],"they":[43],"often":[44,132],"rely":[45],"joint":[47],"supervision":[48],"at":[49],"region":[51],"pixel":[53],"levels":[54],"exploit":[56],"task":[57],"complementarities.":[58],"contrast,":[60],"C<sup":[61,114],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[62,71,115,146,148,150,171,197],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3</sup>VG":[63,116],"explores":[64],"relatively":[66],"under-addressed":[67],"problem":[68],"<italic":[70,145,170,196],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">consistency":[72],"across":[73],"predictions</i>.":[75],"To":[76,139],"end,":[78],"a":[79,86,169,195],"grounding":[82,122],"framework":[83],"based":[84],"coarse-to-fine":[87],"architecture":[88],"is":[89,117],"introduced.":[90],"Empirical":[91],"studies":[92],"demonstrate":[93,227],"that":[94,176,202],"incorporation":[96],"implicit":[99],"explicit":[101],"constraints":[103],"substantially":[104],"enhances":[105,212],"coherence":[107],"between":[108],"detection":[109],"segmentation":[111],"outputs.":[112],"However,":[113],"restricted":[118],"single-referent":[120],"scenarios":[123],"exhibits":[125],"limited":[126],"generalizability":[127,231],"real-world":[129],"applications,":[130],"which":[131,152],"involve":[133],"multi-referents":[134],"or":[135],"even":[136],"absent":[137],"referent.":[138],"overcome":[140],"these":[141],"limitations,":[142],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">GC</i><sup":[147],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3</sup><italic":[149],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">VG</i>,":[151],"incorporates":[153],"three":[154],"key":[155],"advancements:":[156],"(1)":[157],"extension":[158],"scenarios,":[161],"including":[162],"multi-referent":[164],"non-referent":[166],"cases;":[167],"(2)":[168],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Unified":[172],"Coherent":[173],"Refinement":[174],"Module</i>":[175],"implicitly":[177],"encodes":[178],"region-":[179],"instance-level":[181],"features":[182],"while":[183],"explicitly":[184],"modeling":[185],"their":[186],"relational":[187],"alignment":[188],"through":[189],"IoUbased":[191],"constraint;":[192],"(3)":[194],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Granularity-aware":[198],"Hard-mining":[199],"Alignment</i>":[200],"strategy":[201],"enforces":[203],"feature":[208],"space":[209],"simultaneously":[211],"discriminative":[214],"power":[215],"representations.":[220],"Extensive":[221],"experiments":[222],"RefCOCO/+/g":[224],"gRefCOCO":[226],"effectiveness":[229],"proposed":[234],"framework.":[235]},"counts_by_year":[],"updated_date":"2026-04-07T06:01:17.266235","created_date":"2025-11-13T00:00:00"}