{"id":"https://openalex.org/W4414760370","doi":"https://doi.org/10.1109/iccv51701.2025.00663","title":"PropVG: End-To-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination","display_name":"PropVG: End-To-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414760370","doi":"https://doi.org/10.1109/iccv51701.2025.00663"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.04833","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111929740","display_name":"Ming Dai","orcid":"https://orcid.org/0000-0002-4348-6771"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Dai","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068926305","display_name":"Wenxuan Cheng","orcid":"https://orcid.org/0000-0003-1734-5139"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxuan Cheng","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"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":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059524537","display_name":"Jiangjiang Liu","orcid":"https://orcid.org/0000-0002-1341-2763"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang-Jiang Liu","raw_affiliation_strings":["Baidu VIS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu VIS","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100536539","display_name":"Hongshen Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongshen Zhao","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"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":["Jiangnan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangnan University","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074121246","display_name":"Wankou Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wankou Yang","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7058","last_page":"7068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9973000288009644,"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":0.9936000108718872,"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/object","display_name":"Object (grammar)","score":0.6164000034332275},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5453000068664551},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4812000095844269},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.44440001249313354},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.4081999957561493},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.39239999651908875},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.3732999861240387},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.35409998893737793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7587000131607056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6531000137329102},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6164000034332275},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5453000068664551},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4812000095844269},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4560000002384186},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.44440001249313354},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.4081999957561493},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3456999957561493},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3343000113964081},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.31049999594688416},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C2994428975","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word identification","level":4,"score":0.2596000134944916},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2524999976158142},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.04833","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.04833","pdf_url":"https://arxiv.org/pdf/2509.04833","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2509.04833","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.04833","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.04833","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.04833","pdf_url":"https://arxiv.org/pdf/2509.04833","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8015826033","display_name":null,"funder_award_id":"62276061,62436002","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":{"Recent":[0],"advances":[1],"in":[2,62,124],"visual":[3],"grounding":[4],"have":[5],"largely":[6],"shifted":[7],"away":[8],"from":[9],"traditional":[10],"proposal-based":[11,74],"two-stage":[12],"frameworks":[13],"due":[14],"to":[15,51,77,86,120,145],"their":[16],"inefficiency":[17],"and":[18,117,126,142,159,170],"high":[19],"computational":[20],"complexity,":[21],"favoring":[22],"end-to-end":[23,73],"direct":[24],"reference":[25],"paradigms.":[26],"However,":[27],"these":[28,67],"methods":[29],"rely":[30],"exclusively":[31],"on":[32,154],"the":[33,39,78,84,122,147,164],"referred":[34,128],"target":[35],"for":[36,58],"supervision,":[37],"overlooking":[38],"potential":[40],"benefits":[41],"of":[42,80,149,166],"prominent":[43],"prospective":[44],"targets.":[45,151],"Moreover,":[46],"existing":[47],"approaches":[48],"often":[49],"fail":[50],"incorporate":[52],"multi-granularity":[53],"discrimination,":[54],"which":[55,110],"is":[56,83],"crucial":[57],"robust":[59],"object":[60,90,95],"identification":[61],"complex":[63],"scenarios.":[64],"To":[65],"address":[66],"limitations,":[68],"we":[69,102,131],"propose":[70],"PropVG,":[71],"an":[72],"framework":[75],"that,":[76],"best":[79],"our":[81],"knowledge,":[82],"first":[85],"seamlessly":[87],"integrate":[88],"foreground":[89],"proposal":[91],"generation":[92],"with":[93],"referential":[94],"comprehension":[96],"without":[97],"requiring":[98],"additional":[99],"detectors.":[100],"Furthermore,":[101],"introduce":[103],"a":[104,133],"Contrastive-based":[105],"Refer":[106],"Scoring":[107],"(CRS)":[108],"module,":[109],"employs":[111],"contrastive":[112],"learning":[113],"at":[114,174],"both":[115],"sentence":[116],"word":[118],"levels":[119],"enhance":[121],"capability":[123],"understanding":[125],"distinguishing":[127],"objects.":[129],"Additionally,":[130],"design":[132],"Multi-granularity":[134],"Target":[135],"Discrimination":[136],"(MTD)":[137],"module":[138],"that":[139],"fuses":[140],"object-":[141],"semantic-level":[143],"information":[144],"improve":[146],"recognition":[148],"absent":[150],"Extensive":[152],"experiments":[153],"gRefCOCO":[155],"(GREC/GRES),":[156],"Ref-ZOM,":[157],"R-RefCOCO,":[158],"RefCOCO":[160],"(REC/RES)":[161],"benchmarks":[162],"demonstrate":[163],"effectiveness":[165],"PropVG.":[167],"The":[168],"codes":[169],"models":[171],"are":[172],"available":[173],"https://github.com/Dmmm1997/PropVG.":[175]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}