{"id":"https://openalex.org/W4309490634","doi":"https://doi.org/10.1007/s11263-022-01703-8","title":"Recurrent Graph Neural Networks for Video Instance Segmentation","display_name":"Recurrent Graph Neural Networks for Video Instance Segmentation","publication_year":2022,"publication_date":"2022-11-18","ids":{"openalex":"https://openalex.org/W4309490634","doi":"https://doi.org/10.1007/s11263-022-01703-8"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-022-01703-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-022-01703-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-022-01703-8.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"book-chapter","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-022-01703-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001393164","display_name":"Emil Brissman","orcid":"https://orcid.org/0000-0002-0418-9694"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]},{"id":"https://openalex.org/I4210153572","display_name":"Saab (Sweden)","ror":"https://ror.org/05kyy7d06","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210153572"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Emil Brissman","raw_affiliation_strings":["Computer Vision Laboratory, Department of Electrical Engineering, Link\u00f6ping University, Link\u00f6ping, Sweden","Saab, Link\u00f6ping, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Laboratory, Department of Electrical Engineering, Link\u00f6ping University, Link\u00f6ping, Sweden","institution_ids":["https://openalex.org/I102134673"]},{"raw_affiliation_string":"Saab, Link\u00f6ping, Sweden","institution_ids":["https://openalex.org/I4210153572"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037299085","display_name":"Joakim Johnander","orcid":"https://orcid.org/0000-0003-2553-3367"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]},{"id":"https://openalex.org/I4210086940","display_name":"Zenuity (Sweden)","ror":"https://ror.org/000dpyn16","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210086940"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Joakim Johnander","raw_affiliation_strings":["Computer Vision Laboratory, Department of Electrical Engineering, Link\u00f6ping University, Link\u00f6ping, Sweden","Zenseact, G\u00f6teborg, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-2553-3367","affiliations":[{"raw_affiliation_string":"Computer Vision Laboratory, Department of Electrical Engineering, Link\u00f6ping University, Link\u00f6ping, Sweden","institution_ids":["https://openalex.org/I102134673"]},{"raw_affiliation_string":"Zenseact, G\u00f6teborg, Sweden","institution_ids":["https://openalex.org/I4210086940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068158266","display_name":"Martin Danelljan","orcid":"https://orcid.org/0000-0001-6144-9520"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Martin Danelljan","raw_affiliation_strings":["Computer Vision Lab, ETH Z\u00fcrich, Z\u00fcrich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Lab, ETH Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042087981","display_name":"Michael Felsberg","orcid":"https://orcid.org/0000-0002-6096-3648"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]},{"id":"https://openalex.org/I95023434","display_name":"University of KwaZulu-Natal","ror":"https://ror.org/04qzfn040","country_code":"ZA","type":"education","lineage":["https://openalex.org/I95023434"]}],"countries":["SE","ZA"],"is_corresponding":false,"raw_author_name":"Michael Felsberg","raw_affiliation_strings":["Computer Vision Laboratory, Department of Electrical Engineering, Link\u00f6ping University, Link\u00f6ping, Sweden","School of Engineering, University of KwaZulu-Natal, Durban, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Laboratory, Department of Electrical Engineering, Link\u00f6ping University, Link\u00f6ping, Sweden","institution_ids":["https://openalex.org/I102134673"]},{"raw_affiliation_string":"School of Engineering, University of KwaZulu-Natal, Durban, South Africa","institution_ids":["https://openalex.org/I95023434"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037299085"],"corresponding_institution_ids":["https://openalex.org/I102134673","https://openalex.org/I4210086940"],"apc_list":{"value":3690,"currency":"USD","value_usd":3690},"apc_paid":{"value":3690,"currency":"USD","value_usd":3690},"fwci":5.6263,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.97320397,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"131","issue":"2","first_page":"471","last_page":"495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9991999864578247,"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":0.9991999864578247,"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":0.850857138633728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.690341591835022},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6836991906166077},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5737768411636353},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5152649879455566},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5015709400177002},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4530477523803711},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4224422872066498},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.422307550907135},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.41573601961135864},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39554452896118164},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37196433544158936},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36249834299087524},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.14472949504852295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.850857138633728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.690341591835022},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6836991906166077},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5737768411636353},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5152649879455566},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5015709400177002},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4530477523803711},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4224422872066498},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.422307550907135},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.41573601961135864},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39554452896118164},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37196433544158936},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36249834299087524},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.14472949504852295},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s11263-022-01703-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-022-01703-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-022-01703-8.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},{"id":"pmh:oai:DiVA.org:liu-190196","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-190196","pdf_url":"https://liu.diva-portal.org/smash/get/diva2:1714333/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/583252","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/583252","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Computer Vision, 131","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.3929/ethz-b-000583252","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000583252","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"doi:10.1007/s11263-022-01703-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-022-01703-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-022-01703-8.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322225","display_name":"Link\u00f6pings Universitet","ror":"https://ror.org/05ynxx418"},{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"},{"id":"https://openalex.org/F4320336380","display_name":"National Supercomputer Centre, Link\u00f6pings Universitet","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4309490634.pdf","grobid_xml":"https://content.openalex.org/works/W4309490634.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1689711448","https://openalex.org/W2064675550","https://openalex.org/W2092594871","https://openalex.org/W2116341502","https://openalex.org/W2132320224","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2574271221","https://openalex.org/W2603203130","https://openalex.org/W2612690371","https://openalex.org/W2795587607","https://openalex.org/W2805516822","https://openalex.org/W2916797271","https://openalex.org/W2962825871","https://openalex.org/W2962967409","https://openalex.org/W2963849369","https://openalex.org/W2964086649","https://openalex.org/W2964199361","https://openalex.org/W2982723417","https://openalex.org/W2990745571","https://openalex.org/W2993182889","https://openalex.org/W2996435388","https://openalex.org/W3005170598","https://openalex.org/W3009672847","https://openalex.org/W3034275286","https://openalex.org/W3034499084","https://openalex.org/W3034739212","https://openalex.org/W3035442500","https://openalex.org/W3035564946","https://openalex.org/W3092462694","https://openalex.org/W3096609285","https://openalex.org/W3109372619","https://openalex.org/W3110109236","https://openalex.org/W3138516171","https://openalex.org/W3167949052","https://openalex.org/W3169933013","https://openalex.org/W3170674766","https://openalex.org/W3171516518","https://openalex.org/W3202509201","https://openalex.org/W3208503374","https://openalex.org/W3215556244","https://openalex.org/W4205378506","https://openalex.org/W4212774754","https://openalex.org/W4214613769","https://openalex.org/W4214627427","https://openalex.org/W4288083516","https://openalex.org/W6739901393","https://openalex.org/W6756040250","https://openalex.org/W6780226713","https://openalex.org/W7070189664"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W3008584592","https://openalex.org/W4315434538","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Abstract":[0],"Video":[1],"instance":[2,29,50],"segmentation":[3,30,51],"is":[4,32,53,82,137],"one":[5],"of":[6,76,94,133],"the":[7,20,27,47,92,95,114,130],"core":[8],"problems":[9],"in":[10,66,98],"computer":[11],"vision.":[12],"Formulating":[13],"a":[14,33,42,61,74,87,119],"purely":[15],"learning-based":[16],"method,":[17],"which":[18],"models":[19],"generic":[21],"track":[22],"management":[23],"required":[24],"to":[25],"solve":[26],"video":[28,49],"task,":[31],"highly":[34],"challenging":[35,115],"problem.":[36],"In":[37],"this":[38,57],"work,":[39],"we":[40,59],"propose":[41],"novel":[43],"learning":[44],"framework":[45],"where":[46],"entire":[48],"problem":[52],"modeled":[54],"jointly.":[55],"To":[56],"end,":[58],"design":[60],"graph":[62],"neural":[63],"network":[64],"that":[65,128],"each":[67],"frame":[68],"jointly":[69],"processes":[70],"all":[71],"detections":[72],"and":[73,84,109],"memory":[75],"previously":[77],"seen":[78],"tracks.":[79],"Past":[80],"information":[81],"considered":[83],"processed":[85],"via":[86],"recurrent":[88],"connection.":[89],"We":[90,122],"demonstrate":[91],"effectiveness":[93],"proposed":[96],"approach":[97,102],"comprehensive":[99],"experiments.":[100],"Our":[101],"operates":[103],"online":[104],"at":[105,139],"over":[106],"25":[107],"FPS":[108],"obtains":[110],"16.3":[111],"AP":[112],"on":[113],"OVIS":[116],"benchmark,":[117],"setting":[118],"new":[120],"state-of-the-art.":[121],"further":[123],"conduct":[124],"detailed":[125],"ablative":[126],"experiments":[127],"validate":[129],"different":[131],"aspects":[132],"our":[134],"approach.":[135],"Code":[136],"available":[138],"https://github.com/emibr948/RGNNVIS-PlusPlus":[140],".":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-08-08T07:41:36.138363","created_date":"2025-10-10T00:00:00"}