{"id":"https://openalex.org/W3109120382","doi":"https://doi.org/10.1109/tpami.2020.3040258","title":"Zero-Shot Video Object Segmentation with Co-Attention Siamese Networks","display_name":"Zero-Shot Video Object Segmentation with Co-Attention Siamese Networks","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3109120382","doi":"https://doi.org/10.1109/tpami.2020.3040258","mag":"3109120382","pmid":"https://pubmed.ncbi.nlm.nih.gov/33232224"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2020.3040258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2020.3040258","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081796777","display_name":"Xiankai Lu","orcid":"https://orcid.org/0000-0002-9543-6960"},"institutions":[{"id":"https://openalex.org/I4210104151","display_name":"Shangdong Agriculture and Engineering University","ror":"https://ror.org/01px1ve30","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104151"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiankai Lu","raw_affiliation_strings":["School of Software, Shangdong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Shangdong University, Jinan, China","institution_ids":["https://openalex.org/I4210104151"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101433884","display_name":"Wenguan Wang","orcid":"https://orcid.org/0000-0002-0802-9567"},"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":"Wenguan Wang","raw_affiliation_strings":["ETH Zurich, Zrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023184215","display_name":"Jianbing Shen","orcid":"https://orcid.org/0000-0002-4109-8353"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Jianbing Shen","raw_affiliation_strings":["Department of Computer and Information Science, State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China","institution_ids":["https://openalex.org/I6469544","https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003268415","display_name":"David Crandall","orcid":"https://orcid.org/0000-0002-5827-5344"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Crandall","raw_affiliation_strings":["School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055469774","display_name":"Jiebo Luo","orcid":"https://orcid.org/0000-0002-4516-9729"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["Department of Computer Scienece, University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Scienece, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081796777"],"corresponding_institution_ids":["https://openalex.org/I4210104151"],"apc_list":null,"apc_paid":null,"fwci":10.895,"has_fulltext":false,"cited_by_count":140,"citation_normalized_percentile":{"value":0.98805106,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"44","issue":"4","first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"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":1.0,"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":0.998199999332428,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9973000288009644,"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":0.83610600233078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7502216100692749},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7085362672805786},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7057552933692932},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5947673320770264},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5861731171607971},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5779932141304016},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5420925617218018},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5238708853721619},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5089948177337646},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.502408504486084},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4758313000202179},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4713803231716156},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45367664098739624},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.45008793473243713},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4111473560333252},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.292436420917511}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.83610600233078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7502216100692749},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7085362672805786},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7057552933692932},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5947673320770264},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5861731171607971},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5779932141304016},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5420925617218018},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5238708853721619},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5089948177337646},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.502408504486084},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4758313000202179},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4713803231716156},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45367664098739624},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.45008793473243713},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4111473560333252},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.292436420917511},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2020.3040258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2020.3040258","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:33232224","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33232224","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7099999785423279,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":95,"referenced_works":["https://openalex.org/W1496571393","https://openalex.org/W1907877624","https://openalex.org/W1941318923","https://openalex.org/W1973054923","https://openalex.org/W1989348325","https://openalex.org/W2016163842","https://openalex.org/W2030346542","https://openalex.org/W2039313011","https://openalex.org/W2041628650","https://openalex.org/W2074753351","https://openalex.org/W2076756823","https://openalex.org/W2081432165","https://openalex.org/W2096979710","https://openalex.org/W2105482032","https://openalex.org/W2113708607","https://openalex.org/W2117539524","https://openalex.org/W2125930537","https://openalex.org/W2129822853","https://openalex.org/W2137420925","https://openalex.org/W2154071538","https://openalex.org/W2155598147","https://openalex.org/W2156252543","https://openalex.org/W2167331599","https://openalex.org/W2194775991","https://openalex.org/W2197046994","https://openalex.org/W2212077366","https://openalex.org/W2259424905","https://openalex.org/W2302086703","https://openalex.org/W2322739735","https://openalex.org/W2460260369","https://openalex.org/W2462481369","https://openalex.org/W2470139095","https://openalex.org/W2518874898","https://openalex.org/W2550553598","https://openalex.org/W2552391848","https://openalex.org/W2553902701","https://openalex.org/W2562457735","https://openalex.org/W2564998703","https://openalex.org/W2566030665","https://openalex.org/W2575671312","https://openalex.org/W2585592883","https://openalex.org/W2610147486","https://openalex.org/W2612135493","https://openalex.org/W2630837129","https://openalex.org/W2737008123","https://openalex.org/W2752782242","https://openalex.org/W2757028014","https://openalex.org/W2792215676","https://openalex.org/W2794847483","https://openalex.org/W2798441772","https://openalex.org/W2799108379","https://openalex.org/W2799157347","https://openalex.org/W2799239273","https://openalex.org/W2822349497","https://openalex.org/W2883697687","https://openalex.org/W2889658408","https://openalex.org/W2890853604","https://openalex.org/W2894890793","https://openalex.org/W2895340898","https://openalex.org/W2896862475","https://openalex.org/W2921653116","https://openalex.org/W2955060956","https://openalex.org/W2955084925","https://openalex.org/W2962825871","https://openalex.org/W2963091558","https://openalex.org/W2963131444","https://openalex.org/W2963176022","https://openalex.org/W2963253279","https://openalex.org/W2963395775","https://openalex.org/W2963407932","https://openalex.org/W2963548592","https://openalex.org/W2963623904","https://openalex.org/W2963983744","https://openalex.org/W2964130064","https://openalex.org/W2964226882","https://openalex.org/W2967045987","https://openalex.org/W2967199722","https://openalex.org/W2986056979","https://openalex.org/W2987391422","https://openalex.org/W2997217064","https://openalex.org/W2999458807","https://openalex.org/W3034577617","https://openalex.org/W3035295069","https://openalex.org/W3117097536","https://openalex.org/W4239147634","https://openalex.org/W6618372016","https://openalex.org/W6630875275","https://openalex.org/W6678818196","https://openalex.org/W6682137061","https://openalex.org/W6719057275","https://openalex.org/W6727420689","https://openalex.org/W6729263887","https://openalex.org/W6739696289","https://openalex.org/W6739901393","https://openalex.org/W6748666111"],"related_works":["https://openalex.org/W3208297503","https://openalex.org/W156213964","https://openalex.org/W3119773509","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W2050960118","https://openalex.org/W4388405611","https://openalex.org/W2619127353","https://openalex.org/W2786094008","https://openalex.org/W3131501806"],"abstract_inverted_index":{"We":[0,22,115],"introduce":[1],"a":[2,19,32,86,92,180],"novel":[3],"network,":[4],"called":[5],"CO-attention":[6],"siamese":[7],"network":[8],"(COSNet),":[9],"to":[10,36,155],"address":[11],"the":[12,24,39,110,137,140,157,176],"zero-shot":[13],"video":[14,28,123],"object":[15],"segmentation":[16,138],"task":[17],"in":[18,57,64],"holistic":[20],"fashion.":[21],"exploit":[23],"inherent":[25],"correlation":[26],"among":[27],"frames":[29,150],"and":[30,55,68,75,81,94,125,131,160],"incorporate":[31],"global":[33,73],"co-attention":[34,62,83,100,141],"mechanism":[35],"further":[37],"improve":[38],"state-of-the-art":[40],"deep":[41],"learning":[42,49,134],"based":[43],"solutions":[44],"that":[45,173],"primarily":[46],"focus":[47],"on":[48],"discriminative":[50],"foreground":[51,162],"representations":[52],"over":[53,168],"appearance":[54],"motion":[56],"short-term":[58],"temporal":[59],"segments.":[60],"The":[61],"layers":[63],"COSNet":[65,90,117,174],"provide":[66],"efficient":[67],"competent":[69],"stages":[70],"for":[71,105],"capturing":[72,106],"correlations":[74],"scene":[76],"context":[77],"by":[78,146,179],"jointly":[79],"computing":[80],"appending":[82],"responses":[84],"into":[85],"joint":[87,112],"feature":[88,113],"space.":[89,114],"is":[91,153],"unified":[93],"end-to-end":[95],"trainable":[96],"framework":[97],"where":[98],"different":[99],"variants":[101],"can":[102],"be":[103],"derived":[104],"diverse":[107],"properties":[108],"of":[109,122],"learned":[111],"train":[116],"with":[118],"pairs":[119],"(or":[120],"groups)":[121],"frames,":[124],"this":[126],"naturally":[127],"augments":[128],"training":[129],"data":[130],"allows":[132],"increased":[133],"capacity.":[135],"During":[136],"stage,":[139],"model":[142],"encodes":[143],"useful":[144],"information":[145],"processing":[147],"multiple":[148],"reference":[149],"together,":[151],"which":[152],"leveraged":[154],"infer":[156],"frequently":[158],"reappearing":[159],"salient":[161],"objects":[163],"better.":[164],"Our":[165,183],"extensive":[166],"experiments":[167],"three":[169],"large":[170,181],"benchmarks":[171],"demonstrate":[172],"outperforms":[175],"current":[177],"alternatives":[178],"margin.":[182],"implementations":[184],"are":[185],"available":[186],"at":[187],"https://github.com/carrierlxk/COSNet.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":47},{"year":2022,"cited_by_count":52},{"year":2021,"cited_by_count":12}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}