{"id":"https://openalex.org/W3019634314","doi":"https://doi.org/10.1109/icpr48806.2021.9412409","title":"Revisiting Sequence-to-Sequence Video Object Segmentation with Multi-Task Loss and Skip-Memory","display_name":"Revisiting Sequence-to-Sequence Video Object Segmentation with Multi-Task Loss and Skip-Memory","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3019634314","doi":"https://doi.org/10.1109/icpr48806.2021.9412409","mag":"3019634314"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.12170","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088285773","display_name":"Fatemeh Azimi","orcid":"https://orcid.org/0000-0001-9995-0142"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Fatemeh Azimi","raw_affiliation_strings":["TU Kaiserslautern, Kaiserslautern, Germany","German Research Centre for Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"TU Kaiserslautern, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]},{"raw_affiliation_string":"German Research Centre for Artificial Intelligence","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033808296","display_name":"Benjamin Bischke","orcid":"https://orcid.org/0000-0002-6473-3348"},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benjamin Bischke","raw_affiliation_strings":["TU Kaiserslautern, Kaiserslautern, Germany","TU Kaiserslautern, Kaiserslautern Germany"],"affiliations":[{"raw_affiliation_string":"TU Kaiserslautern, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]},{"raw_affiliation_string":"TU Kaiserslautern, Kaiserslautern Germany","institution_ids":["https://openalex.org/I153267046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006074105","display_name":"Sebastian Palacio","orcid":"https://orcid.org/0000-0002-8656-9569"},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Palacio","raw_affiliation_strings":["TU Kaiserslautern, Kaiserslautern, Germany","TU Kaiserslautern, Kaiserslautern Germany"],"affiliations":[{"raw_affiliation_string":"TU Kaiserslautern, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]},{"raw_affiliation_string":"TU Kaiserslautern, Kaiserslautern Germany","institution_ids":["https://openalex.org/I153267046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029509133","display_name":"Federico Raue","orcid":"https://orcid.org/0000-0002-8604-6207"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Federico Raue","raw_affiliation_strings":["DFKI GmbH"],"affiliations":[{"raw_affiliation_string":"DFKI GmbH","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051548778","display_name":"Joern Hees","orcid":null},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jorn Hees","raw_affiliation_strings":["DFKI GmbH"],"affiliations":[{"raw_affiliation_string":"DFKI GmbH","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101904182","display_name":"Andreas Dengel","orcid":"https://orcid.org/0000-0002-6100-8255"},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Dengel","raw_affiliation_strings":["TU Kaiserslautern, Kaiserslautern, Germany","TU Kaiserslautern, Kaiserslautern Germany"],"affiliations":[{"raw_affiliation_string":"TU Kaiserslautern, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]},{"raw_affiliation_string":"TU Kaiserslautern, Kaiserslautern Germany","institution_ids":["https://openalex.org/I153267046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5088285773"],"corresponding_institution_ids":["https://openalex.org/I153267046","https://openalex.org/I33256026"],"apc_list":null,"apc_paid":null,"fwci":0.0969,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.33894706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"5376","last_page":"5383"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9998999834060669,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9998999834060669,"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":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8000167608261108},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7868449687957764},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7024953365325928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6995994448661804},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6884835362434387},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6587618589401245},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6347155570983887},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.615877091884613},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5689182877540588},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5320205688476562},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.44905686378479004},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40223848819732666},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.3972616195678711},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.35067301988601685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8000167608261108},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7868449687957764},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7024953365325928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6995994448661804},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6884835362434387},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6587618589401245},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6347155570983887},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.615877091884613},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5689182877540588},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5320205688476562},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.44905686378479004},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40223848819732666},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.3972616195678711},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.35067301988601685},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.12170","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.12170","pdf_url":"https://arxiv.org/pdf/2004.12170","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2004.12170","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.12170","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3019634314","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.12170","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.12170","pdf_url":"https://arxiv.org/pdf/2004.12170","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320310969","display_name":"Technische Universit\u00e4t Kaiserslautern","ror":"https://ror.org/04zrf7b53"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3019634314.pdf","grobid_xml":"https://content.openalex.org/works/W3019634314.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W589665618","https://openalex.org/W1485009520","https://openalex.org/W1496571393","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1686810756","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2030346542","https://openalex.org/W2031489346","https://openalex.org/W2096979710","https://openalex.org/W2113708607","https://openalex.org/W2161236525","https://openalex.org/W2200599981","https://openalex.org/W2322739735","https://openalex.org/W2402395722","https://openalex.org/W2463175074","https://openalex.org/W2470139095","https://openalex.org/W2564998703","https://openalex.org/W2610147486","https://openalex.org/W2624871570","https://openalex.org/W2739916914","https://openalex.org/W2772283977","https://openalex.org/W2799157347","https://openalex.org/W2890447039","https://openalex.org/W2894961607","https://openalex.org/W2911981226","https://openalex.org/W2916743882","https://openalex.org/W2921536280","https://openalex.org/W2936997284","https://openalex.org/W2962825871","https://openalex.org/W2963150697","https://openalex.org/W2963253279","https://openalex.org/W2963732700","https://openalex.org/W2963881378","https://openalex.org/W2964218467","https://openalex.org/W2964343881","https://openalex.org/W2971095420","https://openalex.org/W2972421837","https://openalex.org/W6617526114","https://openalex.org/W6618372016","https://openalex.org/W6631943919","https://openalex.org/W6639824700","https://openalex.org/W6682137061","https://openalex.org/W6684191040","https://openalex.org/W6743968950","https://openalex.org/W6753214761"],"related_works":["https://openalex.org/W2916797271","https://openalex.org/W2787709582","https://openalex.org/W3172675153","https://openalex.org/W2785358517","https://openalex.org/W2809110088","https://openalex.org/W3110554406","https://openalex.org/W2964221652","https://openalex.org/W3173914571","https://openalex.org/W2968979722","https://openalex.org/W849456794","https://openalex.org/W2994014485","https://openalex.org/W3158673744","https://openalex.org/W2995220146","https://openalex.org/W3174598330","https://openalex.org/W2900866423","https://openalex.org/W2557406251","https://openalex.org/W3135859438","https://openalex.org/W3174463325","https://openalex.org/W3205119183","https://openalex.org/W3135982274"],"abstract_inverted_index":{"Video":[0],"Object":[1],"Segmentation":[2],"(VOS)":[3],"is":[4,18,34,72],"an":[5,88,122],"active":[6],"research":[7],"area":[8],"of":[9,14,45,59,134,146],"the":[10,25,29,32,40,43,46,52,60,70,98,132,144,147,154,159,167],"visual":[11],"domain.":[12],"One":[13],"its":[15],"fundamental":[16],"subtasks":[17],"semi-supervised":[19],"/":[20],"one-shot":[21],"learning:":[22],"given":[23],"only":[24],"segmentation":[26,137,161],"mask":[27],"for":[28,39,96],"first":[30],"frame,":[31],"task":[33,124],"to":[35,143],"provide":[36],"pixel-accurate":[37],"masks":[38],"object":[41,71],"over":[42],"rest":[44],"sequence.":[47],"Despite":[48],"much":[49],"progress":[50],"in":[51,65,136,153],"last":[53],"years,":[54],"we":[55,80,120],"noticed":[56],"that":[57,86,110],"many":[58],"existing":[61],"approaches":[62],"lose":[63],"objects":[64],"longer":[66],"sequences,":[67],"especially":[68],"when":[69],"small":[73],"or":[74],"briefly":[75],"occluded.":[76],"In":[77],"this":[78,104],"work,":[79],"build":[81],"upon":[82],"a":[83,93,108],"sequence-to-sequence":[84],"approach":[85,105,142],"employs":[87],"encoder-decoder":[89],"architecture":[90],"together":[91],"with":[92],"memory":[94],"module":[95],"exploiting":[97],"sequential":[99],"data.":[100],"We":[101,139],"further":[102],"improve":[103],"by":[106],"proposing":[107],"model":[109],"manipulates":[111],"multiscale":[112],"spatio-temporal":[113],"information":[114],"using":[115],"memory-equipped":[116],"skip":[117],"connections.":[118],"Furthermore,":[119],"incorporate":[121],"auxiliary":[123],"based":[125],"on":[126],"distance":[127],"classification":[128],"which":[129],"greatly":[130],"enhances":[131],"quality":[133],"edges":[135],"masks.":[138],"compare":[140],"our":[141],"state":[145],"art":[148],"and":[149,158,166],"show":[150],"considerable":[151],"improvement":[152],"contour":[155],"accuracy":[156],"metric":[157],"overall":[160],"accuracy.":[162],"Our":[163],"source":[164],"code":[165],"pre-trained":[168],"weights":[169],"are":[170],"publicly":[171],"available":[172],"<sup":[173],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[174],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">11</sup>":[175],"https://github.com/fatemehazimi990/RS2S.":[176]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}