{"id":"https://openalex.org/W3207217988","doi":"https://doi.org/10.1145/3474085.3475342","title":"Learning Hierarchical Embedding for Video Instance Segmentation","display_name":"Learning Hierarchical Embedding for Video Instance Segmentation","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3207217988","doi":"https://doi.org/10.1145/3474085.3475342","mag":"3207217988"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475342","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475342","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475342","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475342","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062453382","display_name":"Zheyun Qin","orcid":"https://orcid.org/0000-0003-2564-071X"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheyun Qin","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081796777","display_name":"Xiankai Lu","orcid":"https://orcid.org/0000-0002-9543-6960"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiankai Lu","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019824207","display_name":"Xiushan Nie","orcid":"https://orcid.org/0000-0001-9644-9723"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiushan Nie","raw_affiliation_strings":["Shandong Jianzhu University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026486701","display_name":"Xiantong Zhen","orcid":"https://orcid.org/0000-0001-5213-0462"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Xiantong Zhen","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100672586","display_name":"Yilong Yin","orcid":"https://orcid.org/0000-0001-8341-8792"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilong Yin","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1454,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86536557,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1884","last_page":"1892"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9991000294685364,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.998199999332428,"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":0.7762358784675598},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7682328224182129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7350295186042786},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6480470895767212},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6241103410720825},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5348958373069763},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4914964437484741},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48898613452911377},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.45267581939697266},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4513477683067322},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.43732336163520813},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.43407657742500305},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2688449025154114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7762358784675598},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7682328224182129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7350295186042786},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6480470895767212},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6241103410720825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5348958373069763},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4914964437484741},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48898613452911377},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.45267581939697266},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4513477683067322},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43732336163520813},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.43407657742500305},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2688449025154114},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3474085.3475342","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475342","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475342","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:publications/81a631cb-fceb-4886-b474-db66210e0fd2","is_oa":true,"landing_page_url":"http://hdl.handle.net/11245.1/81a631cb-fceb-4886-b474-db66210e0fd2","pdf_url":"https://pure.uva.nl/ws/files/69445370/3474085.3475342.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Qin, Z, Lu, X, Nie, X, Zhen, X & Yin, Y 2021, Learning Hierarchical Embedding for Video Instance Segmentation. in MM '21 : Proceedings of the 29th ACM International Conference on Multimedia : October 20-24, 2021, Virtual Event, China. Association for Computing Machinery, New York, NY, pp. 1884-1892, 29th ACM International Conference on Multimedia, MM 2021, Virtual, Online, China, 20/10/21. https://doi.org/10.1145/3474085.3475342","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dare.uva.nl:openaire/81a631cb-fceb-4886-b474-db66210e0fd2","is_oa":true,"landing_page_url":"https://hdl.handle.net/11245.1/81a631cb-fceb-4886-b474-db66210e0fd2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Qin, Z, Lu, X, Nie, X, Zhen, X & Yin, Y 2021, Learning Hierarchical Embedding for Video Instance Segmentation. in MM '21 : Proceedings of the 29th ACM International Conference on Multimedia : October 20-24, 2021, Virtual Event, China. Association for Computing Machinery, New York, NY, pp. 1884-1892, 29th ACM International Conference on Multimedia, MM 2021, Virtual, Online, China, 20/10/21. https://doi.org/10.1145/3474085.3475342","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/81a631cb-fceb-4886-b474-db66210e0fd2","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/learning-hierarchical-embedding-for-video-instance-segmentation(81a631cb-fceb-4886-b474-db66210e0fd2).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Qin, Z, Lu, X, Nie, X, Zhen, X & Yin, Y 2021, Learning Hierarchical Embedding for Video Instance Segmentation. in MM '21 : Proceedings of the 29th ACM International Conference on Multimedia : October 20-24, 2021, Virtual Event, China. Association for Computing Machinery, New York, NY, pp. 1884-1892, 29th ACM International Conference on Multimedia, MM 2021, Virtual, Online, China, 20/10/21. https://doi.org/10.1145/3474085.3475342","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/81a631cb-fceb-4886-b474-db66210e0fd2","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/learning-hierarchical-embedding-for-video-instance-segmentation(81a631cb-fceb-4886-b474-db66210e0fd2).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MM '21: Proceedings of the 29th ACM International Conference on Multimedia : October 20-24, 2021, Virtual Event, China, 1884 - 1892","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"doi:10.1145/3474085.3475342","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475342","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475342","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311026","display_name":"Shandong University","ror":"https://ror.org/0207yh398"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3207217988.pdf","grobid_xml":"https://content.openalex.org/works/W3207217988.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W299440670","https://openalex.org/W1710476689","https://openalex.org/W1863660263","https://openalex.org/W1959608418","https://openalex.org/W2031489346","https://openalex.org/W2150408100","https://openalex.org/W2194775991","https://openalex.org/W2470139095","https://openalex.org/W2507009361","https://openalex.org/W2585592883","https://openalex.org/W2599765304","https://openalex.org/W2787709582","https://openalex.org/W2792215676","https://openalex.org/W2819579046","https://openalex.org/W2916743882","https://openalex.org/W2921536280","https://openalex.org/W2942930375","https://openalex.org/W2949735689","https://openalex.org/W2950211064","https://openalex.org/W2954340342","https://openalex.org/W2955084925","https://openalex.org/W2957408986","https://openalex.org/W2970971581","https://openalex.org/W2982723417","https://openalex.org/W2984835641","https://openalex.org/W2986615800","https://openalex.org/W2987391422","https://openalex.org/W2991001610","https://openalex.org/W2995962724","https://openalex.org/W2996537443","https://openalex.org/W2999458807","https://openalex.org/W3012594792","https://openalex.org/W3034499084","https://openalex.org/W3034650337","https://openalex.org/W3035295069","https://openalex.org/W3035549667","https://openalex.org/W3035649147","https://openalex.org/W3045495919","https://openalex.org/W3095495550","https://openalex.org/W3109120382","https://openalex.org/W3109372619","https://openalex.org/W3110501021","https://openalex.org/W3117097536","https://openalex.org/W3182236906"],"related_works":["https://openalex.org/W2517104666","https://openalex.org/W2541791370","https://openalex.org/W4223527717","https://openalex.org/W2005437358","https://openalex.org/W2035976912","https://openalex.org/W1669643531","https://openalex.org/W2337415362","https://openalex.org/W2008656436","https://openalex.org/W2134924024","https://openalex.org/W2023558673"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,99,142],"address":[4],"video":[5,82,128,149],"instance":[6,129],"segmentation":[7,130,151],"using":[8],"a":[9,57,81,89,120],"new":[10],"generative":[11,117],"model":[12,47,69],"that":[13],"learns":[14],"effective":[15],"representations":[16],"of":[17,88,108,137],"the":[18,74,106,109,127,135,138],"target":[19],"and":[20,37,49,54],"background":[21],"appearance.":[22],"We":[23,84],"propose":[24],"to":[25,41,72,77,93,103,119,153],"exploit":[26],"hierarchical":[27,65],"structural":[28],"embedding":[29,66],"over":[30,80],"spatio-temporal":[31,96],"space,":[32],"which":[33,61,113],"is":[34,62,70],"compact,":[35],"powerful,":[36],"flexible":[38],"in":[39,56],"contrast":[40],"current":[42],"tracking-by-detection":[43],"methods.":[44],"Specifically,":[45],"our":[46,144],"segments":[48],"tracks":[50],"instances":[51,79],"across":[52],"space":[53],"time":[55],"single":[58],"forward":[59],"pass,":[60],"formulated":[63],"as":[64],"learning.":[67],"The":[68],"trained":[71],"locate":[73],"pixels":[75],"belonging":[76],"specific":[78],"clip.":[83],"firstly":[85],"take":[86],"advantage":[87],"novel":[90],"mixing":[91],"function":[92],"better":[94],"fuse":[95],"embeddings.":[97],"Moreover,":[98],"introduce":[100],"normalizing":[101],"flows":[102,118],"further":[104],"improve":[105],"robustness":[107],"learned":[110],"appearance":[111],"embedding,":[112],"theoretically":[114],"extends":[115],"conventional":[116],"factorized":[121],"conditional":[122],"scheme.":[123],"Comprehensive":[124],"experiments":[125],"on":[126,146],"benchmark,":[131],"i.e.,":[132],"YouTube-VIS,":[133],"demonstrate":[134,154],"effectiveness":[136],"proposed":[139],"approach.":[140],"Furthermore,":[141],"evaluate":[143],"method":[145],"an":[147],"unsupervised":[148],"object":[150],"dataset":[152],"its":[155],"generalizability.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}