{"id":"https://openalex.org/W4414856456","doi":"https://doi.org/10.1109/tmm.2025.3618559","title":"Referring Video Object Segmentation With Cross-Modality Proxy Queries","display_name":"Referring Video Object Segmentation With Cross-Modality Proxy Queries","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414856456","doi":"https://doi.org/10.1109/tmm.2025.3618559"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3618559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3618559","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 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":"https://openalex.org/A5020149992","display_name":"Baoli Sun","orcid":"https://orcid.org/0000-0002-2861-4288"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoli Sun","raw_affiliation_strings":["DUT-RU International School of Information Science & Engineering, Dalian University of Technology, Dalian, China","DUT-RU International School of Information Science & Engineering, Dalian University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-2861-4288","affiliations":[{"raw_affiliation_string":"DUT-RU International School of Information Science & Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"DUT-RU International School of Information Science & Engineering, Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030101527","display_name":"Xinzhu Ma","orcid":"https://orcid.org/0000-0003-0504-0186"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xinzhu Ma","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong SAR, China","Chinese University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-0504-0186","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058107332","display_name":"Ning Wang","orcid":"https://orcid.org/0000-0003-1745-1425"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Wang","raw_affiliation_strings":["DUT-RU International School of Information Science & Engineering, Dalian University of Technology, Dalian, China","DUT-RU International School of Information Science & Engineering, Dalian University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DUT-RU International School of Information Science & Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"DUT-RU International School of Information Science & Engineering, Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhihui Wang","orcid":"https://orcid.org/0000-0002-5011-9726"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Zhihui Wang","raw_affiliation_strings":["DUT-RU International School of Information Science & Engineering, Dalian University of Technology, Dalian, China","University of Sydney, Sydney, NSW, Australia","DUT-RU International School of Information Science & Engineering, Dalian University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-5011-9726","affiliations":[{"raw_affiliation_string":"DUT-RU International School of Information Science & Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"DUT-RU International School of Information Science & Engineering, Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhiyong Wang","orcid":"https://orcid.org/0000-0002-8043-0312"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wang","raw_affiliation_strings":["DUT-RU International School of Information Science & Engineering, Dalian University of Technology, Dalian, China","University of Sydney, Sydney, NSW, Australia","University of Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8043-0312","affiliations":[{"raw_affiliation_string":"DUT-RU International School of Information Science & Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":3,"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":0.23891222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"9659","last_page":"9669"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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":0.9983000159263611,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9923999905586243,"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/video-tracking","display_name":"Video tracking","score":0.6807000041007996},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5353999733924866},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.44359999895095825},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.3801000118255615},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3571000099182129},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3416999876499176},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.32010000944137573},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.31630000472068787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8925999999046326},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.6807000041007996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5942000150680542},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5353999733924866},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44359999895095825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39309999346733093},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.29190000891685486},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2669999897480011},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3618559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3618559","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G39296982","display_name":"Fine-grained Human Action Recognition with Deep Graph Neural Networks","funder_award_id":"DP210102674","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W1905722737","https://openalex.org/W2034014085","https://openalex.org/W2962942822","https://openalex.org/W2963445828","https://openalex.org/W2980088508","https://openalex.org/W3035097537","https://openalex.org/W3035549667","https://openalex.org/W3096609285","https://openalex.org/W3104844437","https://openalex.org/W3122784054","https://openalex.org/W3169367294","https://openalex.org/W3169933013","https://openalex.org/W3170410843","https://openalex.org/W3171516518","https://openalex.org/W3201770677","https://openalex.org/W3206261212","https://openalex.org/W3215899623","https://openalex.org/W4224988000","https://openalex.org/W4226024706","https://openalex.org/W4230920021","https://openalex.org/W4288052482","https://openalex.org/W4312294051","https://openalex.org/W4312297823","https://openalex.org/W4312837597","https://openalex.org/W4312868348","https://openalex.org/W4312981390","https://openalex.org/W4313007081","https://openalex.org/W4313123347","https://openalex.org/W4318954130","https://openalex.org/W4378697079","https://openalex.org/W4385245566","https://openalex.org/W4386071535","https://openalex.org/W4386076040","https://openalex.org/W4386076233","https://openalex.org/W4386108423","https://openalex.org/W4387969495","https://openalex.org/W4388073520","https://openalex.org/W4390872868","https://openalex.org/W4390873204","https://openalex.org/W4390873614","https://openalex.org/W4394593033","https://openalex.org/W4394842360","https://openalex.org/W4395703093","https://openalex.org/W4403085534","https://openalex.org/W4409369752"],"related_works":[],"abstract_inverted_index":{"Referring":[0],"video":[1,107,121,170,177,197,217,231],"object":[2,53,75,187,213],"segmentation":[3],"(RVOS)":[4],"is":[5],"an":[6,30],"emerging":[7],"cross-modality":[8,45,239],"task":[9],"that":[10,175],"aims":[11],"to":[12,145,203,237,258,292],"generate":[13],"pixel-level":[14],"maps":[15],"of":[16,105,142,155,169,188,193,212,289],"the":[17,51,73,80,102,120,126,153,176,186,194,200,208,216,221,263,267,287,293],"target":[18,52,91],"objects":[19],"referred":[20],"by":[21],"given":[22],"textual":[23,114],"expressions.":[24],"The":[25],"main":[26],"concept":[27],"involves":[28],"learning":[29],"accurate":[31,90],"alignment":[32,46],"visual":[33,147],"elements":[34],"and":[35,86,98,108,148,151,162,210,232,244,266,283],"language":[36],"expressions":[37],"within":[38],"a":[39,55,106,132,140,251],"semantic":[40,260],"space.":[41],"Recent":[42],"approaches":[43],"address":[44],"through":[47,79],"conditional":[48,70],"queries,":[49,71,234],"tracking":[50,92,214],"using":[54],"queryresponse":[56],"based":[57],"mechanism":[58],"built":[59],"upon":[60],"transformer":[61],"structure.":[62],"However,":[63],"they":[64,100],"exhibit":[65],"two":[66],"limitations:":[67],"(1)":[68],"these":[69],"identifying":[72],"same":[74,81],"across":[76,166,196],"different":[77],"frames":[78],"query,":[82],"lack":[83],"inter-frame":[84,205],"dependency":[85],"variation":[87],"modeling,":[88],"making":[89],"challenging":[93],"amid":[94],"significant":[95],"frame-to-frame":[96],"variations;":[97],"(2)":[99],"handle":[101],"temporal":[103,243],"feature":[104,171],"build":[109],"visual-language":[110],"interaction":[111],"sequentially,":[112],"integrating":[113],"constraints":[115],"belatedly,":[116],"which":[117,138],"may":[118],"cause":[119],"features":[122,178],"potentially":[123],"focus":[124],"on":[125,185,273],"non-referred":[127],"objects.":[128],"Therefore,":[129],"we":[130,235,249],"propose":[131,236],"novel":[133],"RVOS":[134,277],"architecture":[135],"called":[136],"ProxyFormer,":[137],"introduces":[139],"set":[141],"proxy":[143,164,201,233,264],"queries":[144,165,195,202,265],"integrate":[146],"text":[149],"semantics":[150,156],"facilitate":[152],"flow":[154],"between":[157,230,262],"them.":[158],"By":[159],"progressively":[160],"updating":[161],"propagating":[163],"multiple":[167],"stages":[168],"encoder,":[172],"ProxyFormer":[173,291],"ensures":[174],"are":[179],"as":[180,182],"focused":[181],"much":[183],"possible":[184],"interest.":[189],"This":[190],"dynamic":[191],"evolution":[192],"also":[198],"enables":[199],"establish":[204],"dependencies,":[206],"enhancing":[207],"accuracy":[209],"coherence":[211],"throughout":[215],"sequence.":[218],"To":[219],"mitigate":[220],"high":[222],"computational":[223],"costs":[224],"associated":[225],"with":[226],"full":[227],"spatio-temporal":[228],"interactions":[229,240],"decouple":[238],"into":[241],"their":[242],"spatial":[245],"dimensions,":[246],"respectively.":[247],"Additionally,":[248],"design":[250],"Joint":[252],"Semantic":[253],"Consistency":[254],"(JSC)":[255],"training":[256],"strategy":[257],"align":[259],"consensus":[261],"combined":[268],"videotext":[269],"pairs.":[270],"Comprehensive":[271],"experiments":[272],"four":[274],"widely":[275],"used":[276],"benchmarks,":[278],"i.e.,":[279],"Ref-Youtube-VOS,":[280],"Ref-DAVIS17,":[281],"A2D-Sentences":[282],"JHMDB-Sentences,":[284],"clearly":[285],"demonstrate":[286],"superiority":[288],"our":[290],"state-of-the-art":[294],"methods":[295]},"counts_by_year":[],"updated_date":"2025-12-19T00:32:22.182498","created_date":"2025-10-10T00:00:00"}