{"id":"https://openalex.org/W3176180954","doi":"https://doi.org/10.48550/arxiv.2106.11963","title":"Tracking Instances as Queries","display_name":"Tracking Instances as Queries","publication_year":2021,"publication_date":"2021-06-22","ids":{"openalex":"https://openalex.org/W3176180954","doi":"https://doi.org/10.48550/arxiv.2106.11963","mag":"3176180954"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2106.11963","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.11963","pdf_url":"https://arxiv.org/pdf/2106.11963","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.11963","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004788654","display_name":"Shusheng Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Shusheng","raw_affiliation_strings":["Applied Research Center (ARC) , Tencent PCG","School of EIC , Huazhong University of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Research Center (ARC) , Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"School of EIC , Huazhong University of Science & Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fang, Yuxin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang, Yuxin","raw_affiliation_strings":["School of EIC , Huazhong University of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EIC , Huazhong University of Science & Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037191476","display_name":"Xinggang Wang","orcid":"https://orcid.org/0000-0001-6732-7823","observed_orcids":["https://orcid.org/0000-0001-6732-7823"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Xinggang","raw_affiliation_strings":["School of EIC , Huazhong University of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EIC , Huazhong University of Science & Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345915","display_name":"Yu Li","orcid":"https://orcid.org/0000-0003-1865-8276","observed_orcids":["https://orcid.org/0000-0003-1865-8276"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yu","raw_affiliation_strings":["Applied Research Center (ARC) , Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Research Center (ARC) , Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004349","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0001-7673-8325","observed_orcids":["https://orcid.org/0000-0001-7673-8325"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan, Ying","raw_affiliation_strings":["Applied Research Center (ARC) , Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Research Center (ARC) , Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000885691","display_name":"Bin Feng","orcid":"https://orcid.org/0000-0003-2166-751X","observed_orcids":["https://orcid.org/0000-0003-2166-751X"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng, Bin","raw_affiliation_strings":["School of EIC , Huazhong University of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EIC , Huazhong University of Science & Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100665053","display_name":"Wenyu Liu","orcid":"https://orcid.org/0000-0002-4582-7488","observed_orcids":["https://orcid.org/0000-0002-4582-7488","https://orcid.org/0009-0005-5315-6943","https://orcid.org/0009-0008-7321-572X","https://orcid.org/0009-0008-8368-4685"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Wenyu","raw_affiliation_strings":["School of EIC , Huazhong University of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EIC , Huazhong University of Science & Technology","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5702999830245972,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.5702999830245972,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.33250001072883606,"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":0.04610000178217888,"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-instance-segmentation","display_name":"video instance segmentation","score":0.8980000019073486},{"id":"https://openalex.org/keywords/instance-tracking","display_name":"instance tracking","score":0.6679999828338623},{"id":"https://openalex.org/keywords/end-to-end-learning","display_name":"end-to-end learning","score":0.5600000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8567888736724854},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7686392068862915},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7393984794616699},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5335118770599365},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5114087462425232},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5022072792053223},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4901064336299896},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.48690783977508545},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4720476567745209},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4414112865924835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4261690676212311},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.41815897822380066},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2106.11963","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.11963","pdf_url":"https://arxiv.org/pdf/2106.11963","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.2106.11963","doi":"https://doi.org/10.48550/arxiv.2106.11963","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.11963","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.11963","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.11963","pdf_url":"https://arxiv.org/pdf/2106.11963","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2549139847","https://openalex.org/W2982723417","https://openalex.org/W2994014485","https://openalex.org/W2994982825","https://openalex.org/W3011350702","https://openalex.org/W3084173793","https://openalex.org/W3084874594","https://openalex.org/W3110030584","https://openalex.org/W3110109236","https://openalex.org/W3121480429","https://openalex.org/W3138516171","https://openalex.org/W3139267983","https://openalex.org/W3165926952","https://openalex.org/W3166506074","https://openalex.org/W3170778815","https://openalex.org/W3170841864","https://openalex.org/W3171516518","https://openalex.org/W3172752666","https://openalex.org/W3173980723","https://openalex.org/W3176882925","https://openalex.org/W3202509201","https://openalex.org/W3212743778"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2043093291","https://openalex.org/W4388446985"],"abstract_inverted_index":{"Recently,":[0],"query":[1,37,67],"based":[2,38,68],"deep":[3],"networks":[4],"catch":[5],"lots":[6],"of":[7,120],"attention":[8],"owing":[9],"to":[10,34,51],"their":[11],"end-to-end":[12,112],"pipeline":[13],"and":[14,29,47,79],"competitive":[15],"results":[16,128],"on":[17,91,129],"several":[18],"fundamental":[19],"computer":[20],"vision":[21],"tasks,":[22],"such":[23],"as":[24,63,133],"object":[25],"detection,":[26],"semantic":[27],"segmentation,":[28],"instance":[30,40],"segmentation.":[31],"However,":[32],"how":[33],"establish":[35],"a":[36,65,109],"video":[39],"segmentation":[41],"(VIS)":[42],"framework":[43,70],"with":[44],"elegant":[45],"architecture":[46],"strong":[48],"performance":[49],"remains":[50],"be":[52],"settled.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"present":[58],"\\textbf{QueryTrack}":[59],"(i.e.,":[60],"tracking":[61],"instances":[62,78],"queries),":[64],"unified":[66],"VIS":[69,137],"fully":[71],"leveraging":[72],"the":[73,98,102,136],"intrinsic":[74],"one-to-one":[75],"correspondence":[76],"between":[77],"queries":[80],"in":[81,101],"QueryInst.":[82],"The":[83],"proposed":[84],"method":[85],"obtains":[86],"52.7":[87],"/":[88,93],"52.3":[89],"AP":[90],"YouTube-VIS-2019":[92],"2021":[94,107],"datasets,":[95],"which":[96],"wins":[97],"2-nd":[99],"place":[100],"YouTube-VIS":[103],"Challenge":[104],"at":[105],"CVPR":[106],"\\textbf{with":[108],"single":[110,114],"online":[111],"model,":[113],"scale":[115],"testing":[116],"\\&":[117],"modest":[118],"amount":[119],"training":[121],"data}.":[122],"We":[123],"also":[124],"provide":[125],"QueryTrack-ResNet-50":[126],"baseline":[127],"YouTube-VIS-2021":[130],"val":[131],"set":[132],"references":[134],"for":[135],"community.":[138]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}
