{"id":"https://openalex.org/W4402039847","doi":"https://doi.org/10.1109/tcsvt.2024.3452418","title":"A Masked Reference Token Supervision-Based Iterative Visual-Language Framework for Robust Visual Grounding","display_name":"A Masked Reference Token Supervision-Based Iterative Visual-Language Framework for Robust Visual Grounding","publication_year":2024,"publication_date":"2024-08-30","ids":{"openalex":"https://openalex.org/W4402039847","doi":"https://doi.org/10.1109/tcsvt.2024.3452418"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3452418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3452418","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/A5100710371","display_name":"Chunlei Wang","orcid":"https://orcid.org/0000-0002-8955-9964"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlei Wang","raw_affiliation_strings":["Department of Electronics and Information Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8955-9964","affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037415977","display_name":"Wenquan Feng","orcid":"https://orcid.org/0000-0002-5180-7889"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenquan Feng","raw_affiliation_strings":["Department of Electronics and Information Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5180-7889","affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029244560","display_name":"Shuchang Lyu","orcid":"https://orcid.org/0000-0001-9769-7083"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuchang Lyu","raw_affiliation_strings":["Department of Electronics and Information Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9769-7083","affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115599767","display_name":"Guangliang Cheng","orcid":"https://orcid.org/0000-0001-8686-9513"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guangliang Cheng","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Liverpool, U.K","Department of Computer Science, University of Liverpool, UK"],"raw_orcid":"https://orcid.org/0000-0001-8686-9513","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, U.K","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089900108","display_name":"Xiangtai Li","orcid":"https://orcid.org/0000-0002-0550-8247"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiangtai Li","raw_affiliation_strings":["S-Laboratory, Nanyang Technological University, Jurong West, Singapore","S-Lab, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0550-8247","affiliations":[{"raw_affiliation_string":"S-Laboratory, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052052722","display_name":"Binghao Liu","orcid":"https://orcid.org/0000-0001-6590-0016"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binghao Liu","raw_affiliation_strings":["Department of Electronics and Information Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6590-0016","affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101722127","display_name":"Qi Zhao","orcid":"https://orcid.org/0000-0002-3508-027X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zhao","raw_affiliation_strings":["Department of Electronics and Information Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3508-027X","affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8131,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70563369,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"35","issue":"1","first_page":"75","last_page":"90"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9884999990463257,"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":0.9884999990463257,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9793999791145325,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9682000279426575,"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":0.7101155519485474},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5385623574256897},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5355422496795654},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4840632975101471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4660777747631073},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.44235605001449585},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33709824085235596},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.13658663630485535},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1293623149394989},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09198388457298279}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7101155519485474},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5385623574256897},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5355422496795654},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4840632975101471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4660777747631073},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.44235605001449585},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33709824085235596},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.13658663630485535},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1293623149394989},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09198388457298279}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2024.3452418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3452418","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"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/217682","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/217682","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G169159138","display_name":null,"funder_award_id":"62072021","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":89,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W2194775991","https://openalex.org/W2251512949","https://openalex.org/W2302548814","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2606473278","https://openalex.org/W2745461083","https://openalex.org/W2946086442","https://openalex.org/W2962766617","https://openalex.org/W2963109634","https://openalex.org/W2964345792","https://openalex.org/W2967767914","https://openalex.org/W2970231061","https://openalex.org/W2984121207","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W2997591391","https://openalex.org/W3000172657","https://openalex.org/W3034772468","https://openalex.org/W3035398197","https://openalex.org/W3096609285","https://openalex.org/W3110435696","https://openalex.org/W3131251978","https://openalex.org/W3138516171","https://openalex.org/W3159619744","https://openalex.org/W3173364567","https://openalex.org/W3174004334","https://openalex.org/W3184264821","https://openalex.org/W3184840388","https://openalex.org/W3192658445","https://openalex.org/W4200631575","https://openalex.org/W4214490042","https://openalex.org/W4221166276","https://openalex.org/W4285725668","https://openalex.org/W4289654392","https://openalex.org/W4292828589","https://openalex.org/W4312543911","https://openalex.org/W4312598093","https://openalex.org/W4312844845","https://openalex.org/W4313145013","https://openalex.org/W4361983876","https://openalex.org/W4365808282","https://openalex.org/W4367050941","https://openalex.org/W4367665802","https://openalex.org/W4375928651","https://openalex.org/W4381744346","https://openalex.org/W4382458695","https://openalex.org/W4385245566","https://openalex.org/W4386066126","https://openalex.org/W4387986753","https://openalex.org/W4389352357","https://openalex.org/W4390190349","https://openalex.org/W4390872427","https://openalex.org/W4390872550","https://openalex.org/W4390872619","https://openalex.org/W4390873107","https://openalex.org/W4390873343","https://openalex.org/W4390874575","https://openalex.org/W4392449449","https://openalex.org/W4392543666","https://openalex.org/W4402716271","https://openalex.org/W4402716371","https://openalex.org/W4402727388","https://openalex.org/W4402753325","https://openalex.org/W6631943919","https://openalex.org/W6676647902","https://openalex.org/W6755207826","https://openalex.org/W6757135208","https://openalex.org/W6766904570","https://openalex.org/W6791353385","https://openalex.org/W6798837711","https://openalex.org/W6802517928","https://openalex.org/W6804631322","https://openalex.org/W6838745215","https://openalex.org/W6838787608","https://openalex.org/W6838809002","https://openalex.org/W6840684104","https://openalex.org/W6843661293","https://openalex.org/W6848855029","https://openalex.org/W6850787431","https://openalex.org/W6851607685","https://openalex.org/W6851610920","https://openalex.org/W6854222408","https://openalex.org/W6854420576","https://openalex.org/W6856476805","https://openalex.org/W6857865361"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W2021787609","https://openalex.org/W4387768015"],"abstract_inverted_index":{"Visual":[0,72],"Grounding":[1,73],"(VG)":[2],"has":[3],"become":[4],"a":[5,130,141,186],"prominent":[6],"task":[7],"in":[8,204],"recent":[9],"years,":[10],"achieving":[11],"significant":[12],"advancements":[13],"with":[14,76,91,134,185],"the":[15,29,57,84,111,121,171,214,226,229,233],"development":[16],"of":[17,31,86,113,144,150,173,189,228],"detection":[18],"and":[19,52,60,103,115,137,160,208,222,246],"vision":[20],"transformers.":[21],"However,":[22],"existing":[23,43,155,176],"VG":[24,125,132,158,174,206,218,243],"methods":[25,44,159],"struggle":[26],"to":[27,38,46,82,147,169,193],"handle":[28,170,201],"effects":[30],"inaccurate":[32,92,195],"or":[33],"irrelevant":[34],"textual":[35,61],"descriptions,":[36],"tending":[37],"generate":[39],"false-alarm":[40,87,145,202],"objects.":[41],"Moreover,":[42,232],"fail":[45],"capture":[47],"fine-grained":[48],"features,":[49],"accurate":[50],"localization,":[51],"comprehensive":[53],"context":[54],"understanding":[55],"from":[56],"whole":[58],"image":[59],"descriptions.":[62,197],"To":[63,119],"address":[64],"these":[65],"issues,":[66],"we":[67,128,138],"propose":[68],"an":[69],"Iterative":[70,104],"Robust":[71],"(IR-VG)":[74],"framework":[75,95,235],"Multi-stage":[77],"False-alarm":[78],"Sensitive":[79],"Decoder":[80],"(MFSD)":[81],"prevent":[83],"generation":[85],"objects":[88],"when":[89],"presented":[90],"expressions.":[93],"The":[94],"introduces":[96],"Masked":[97],"Reference":[98],"based":[99],"Centerpoint":[100],"Supervision":[101],"(MRCS)":[102],"Multi-level":[105],"Vision-language":[106],"Fusion":[107],"(IMVF)":[108],"for":[109],"enhancing":[110],"accuracy":[112],"localization":[114],"better":[116],"visual-language":[117],"alignment.":[118],"investigate":[120],"elements":[122],"that":[123,165],"affect":[124],"robustness":[126,172],"further,":[127],"release":[129],"robust":[131,205,217],"benchmark":[133],"24,000":[135],"instances":[136],"also":[139,237],"provide":[140],"detailed":[142],"classification":[143],"according":[146],"different":[148],"parts":[149],"speech.":[151],"Extensive":[152],"experiments":[153,224],"on":[154,213,240],"state-of-the-art":[156],"(SOTA)":[157],"foundation":[161,179],"models":[162,247],"have":[163,182,191],"proven":[164],"it":[166],"is":[167,236],"difficult":[168],"by":[175],"models.":[177],"Even":[178],"models,":[180],"which":[181],"been":[183],"pre-trained":[184],"large":[187],"amount":[188],"data,":[190],"difficulty":[192],"understand":[194],"language":[196],"Our":[198],"IR-VG":[199],"can":[200],"issues":[203],"well":[207],"achieve":[209],"new":[210],"SOTA":[211],"results":[212],"newly":[215],"proposed":[216,230,234],"datasets.":[219,244],"Ablation":[220],"studies":[221],"visualization":[223],"demonstrate":[225],"effectiveness":[227],"components.":[231],"verified":[238],"effective":[239],"five":[241],"regular":[242],"Codes":[245],"will":[248],"be":[249],"publicly":[250],"athttps://github.com/cv516Buaa/IR-VG.":[251]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}