{"id":"https://openalex.org/W4393178550","doi":"https://doi.org/10.1609/aaai.v38i6.28465","title":"Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation","display_name":"Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation","publication_year":2024,"publication_date":"2024-03-24","ids":{"openalex":"https://openalex.org/W4393178550","doi":"https://doi.org/10.1609/aaai.v38i6.28465"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v38i6.28465","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i6.28465","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28465/28905","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28465/28905","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101782494","display_name":"Shilin Yan","orcid":"https://orcid.org/0000-0002-6860-9811"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilin Yan","raw_affiliation_strings":["Fudan Unversity"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan Unversity","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102891082","display_name":"Renrui Zhang","orcid":"https://orcid.org/0000-0003-4503-5277"},"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":"Renrui Zhang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory\nThe Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory\nThe Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziyu Guo","orcid":null},"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":"Ziyu Guo","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100651077","display_name":"Wenchao Chen","orcid":"https://orcid.org/0000-0002-8875-1161"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenchao Chen","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101529083","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0003-4155-5195"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450553","display_name":"Hongyang Li","orcid":"https://orcid.org/0000-0001-9110-5534"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyang Li","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748135","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0002-1889-2567"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Qiao","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709866","display_name":"Hao Dong","orcid":"https://orcid.org/0000-0002-5101-7430"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Dong","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101320954","display_name":"Zhongjiang He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongjiang He","raw_affiliation_strings":["China Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362419","display_name":"Peng Gao","orcid":"https://orcid.org/0000-0003-4398-5471"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Gao","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.209,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.94109772,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"38","issue":"6","first_page":"6449","last_page":"6457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9929999709129333,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9929999709129333,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9926999807357788,"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":0.9919000267982483,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6035364270210266},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5846472978591919},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5799201726913452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5441085696220398},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5421541333198547},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4654702842235565},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1351129710674286}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6035364270210266},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5846472978591919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5799201726913452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5441085696220398},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5421541333198547},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4654702842235565},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1351129710674286},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1609/aaai.v38i6.28465","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i6.28465","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28465/28905","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:hub.hku.hk:10722/351497","is_oa":false,"landing_page_url":"https://hub.hku.hk/handle/10722/351497","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"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":"Conference_Paper"},{"id":"pmh:oai:ojs.aaai.org:article/28465","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/28465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v38i6.28465","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i6.28465","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28465/28905","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6200000047683716,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G8175702131","display_name":null,"funder_award_id":"62206272","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"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393178550.pdf"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2432481613","https://openalex.org/W2526050071","https://openalex.org/W2793407941","https://openalex.org/W2876852810","https://openalex.org/W2884561390","https://openalex.org/W2890447039","https://openalex.org/W2894964039","https://openalex.org/W2936707910","https://openalex.org/W2950628590","https://openalex.org/W2962766617","https://openalex.org/W2962914239","https://openalex.org/W2962942822","https://openalex.org/W2965373594","https://openalex.org/W2980088508","https://openalex.org/W3004019157","https://openalex.org/W3011491087","https://openalex.org/W3034692043","https://openalex.org/W3035097537","https://openalex.org/W3096609285","https://openalex.org/W3104844437","https://openalex.org/W3122411985","https://openalex.org/W3138516171","https://openalex.org/W3170088426","https://openalex.org/W3170630188","https://openalex.org/W3171098737","https://openalex.org/W3191278083","https://openalex.org/W3201770677","https://openalex.org/W3212022073","https://openalex.org/W4200631575","https://openalex.org/W4221152841","https://openalex.org/W4226024706","https://openalex.org/W4281747483","https://openalex.org/W4281839746","https://openalex.org/W4283796148","https://openalex.org/W4286588515","https://openalex.org/W4287653886","https://openalex.org/W4288099632","https://openalex.org/W4304084115","https://openalex.org/W4307504011","https://openalex.org/W4312294051","https://openalex.org/W4312560592","https://openalex.org/W4312690830","https://openalex.org/W4313123347","https://openalex.org/W4313175608","https://openalex.org/W4313447410","https://openalex.org/W4322615526","https://openalex.org/W4323323799","https://openalex.org/W4327534052","https://openalex.org/W4361229539","https://openalex.org/W4362599073","https://openalex.org/W4362679702","https://openalex.org/W4367628410","https://openalex.org/W4368754857","https://openalex.org/W4372283850","https://openalex.org/W4386075985","https://openalex.org/W4386436509","https://openalex.org/W4386555501","https://openalex.org/W4386977985","https://openalex.org/W4387436656","https://openalex.org/W4388685775","https://openalex.org/W4389261656","https://openalex.org/W4389502051","https://openalex.org/W6687483927","https://openalex.org/W6742348326","https://openalex.org/W6778485988","https://openalex.org/W6792812285","https://openalex.org/W6797737728","https://openalex.org/W6804533212","https://openalex.org/W6840058269"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recently,":[0],"video":[1,69,90,135],"object":[2,70,170],"segmentation":[3],"(VOS)":[4],"referred":[5],"by":[6,93],"multi-modal":[7,113,126,208],"signals,":[8],"e.g.,":[9],"language":[10],"and":[11,20,32,48,85,112,148,184,190,196],"audio,":[12],"has":[13],"evoked":[14],"increasing":[15],"attention":[16],"in":[17],"both":[18],"industry":[19],"academia.":[21],"It":[22],"is":[23,86,211],"challenging":[24],"for":[25,45,67,76,116,156,168,177,206],"exploring":[26],"the":[27,33,50,77,107,121,125,140,150,161,180],"semantic":[28,151],"alignment":[29,152],"within":[30],"modalities":[31],"visual":[34,131],"correspondence":[35,176],"across":[36],"frames.":[37,136],"However,":[38],"existing":[39],"methods":[40],"adopt":[41],"separate":[42],"network":[43],"architectures":[44],"different":[46,169],"modalities,":[47],"neglect":[49],"inter-frame":[51,165],"temporal":[52,108,118,146,158],"interaction":[53,159],"with":[54,145,187],"references.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,100,123,163],"propose":[60],"MUTR,":[61],"a":[62,73,82],"Multi-modal":[63],"Unified":[64],"Temporal":[65],"transformer":[66,84],"Referring":[68],"segmentation.":[71],"With":[72],"unified":[74,207],"framework":[75],"first":[78],"time,":[79],"MUTR":[80,193],"adopts":[81],"DETR-style":[83],"capable":[87],"of":[88],"segmenting":[89],"objects":[91],"designated":[92],"either":[94],"text":[95,141,189],"or":[96,142],"audio":[97,143,191],"reference.":[98],"Specifically,":[99],"introduce":[101],"two":[102],"strategies":[103],"to":[104,128,173,200],"fully":[105],"explore":[106],"relations":[109],"between":[110,153],"videos":[111],"signals.":[114],"Firstly,":[115],"low-level":[117],"aggregation":[119],"before":[120],"transformer,":[122,162],"enable":[124],"references":[127],"capture":[129],"multi-scale":[130],"cues":[132],"from":[133],"consecutive":[134],"This":[137],"effectively":[138],"endows":[139],"signals":[144],"knowledge":[147],"boosts":[149],"modalities.":[154],"Secondly,":[155],"high-level":[157],"after":[160],"conduct":[164],"feature":[166],"communication":[167],"embeddings,":[171],"contributing":[172],"better":[174],"object-wise":[175],"tracking":[178],"along":[179],"video.":[181],"On":[182],"Ref-YouTube-VOS":[183],"AVSBench":[185],"datasets":[186],"respective":[188],"references,":[192],"achieves":[194],"+4.2%":[195],"+8.7%":[197],"J&F":[198],"improvements":[199],"state-of-the-art":[201],"methods,":[202],"demonstrating":[203],"our":[204],"significance":[205],"VOS.":[209],"Code":[210],"released":[212],"at":[213],"https://github.com/OpenGVLab/MUTR.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}