{"id":"https://openalex.org/W2953500328","doi":null,"title":"A Spectral Approach to Unsupervised Object Segmentation in Video","display_name":"A Spectral Approach to Unsupervised Object Segmentation in Video","publication_year":2019,"publication_date":"2019-07-05","ids":{"openalex":"https://openalex.org/W2953500328","mag":"2953500328"},"language":"en","primary_location":{"id":"mag:2953500328","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1907.02731v1","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/1907.02731v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067714965","display_name":"Elena Burceanu","orcid":"https://orcid.org/0000-0001-8612-0895","observed_orcids":["https://orcid.org/0000-0001-8612-0895"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elena Burceanu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086392501","display_name":"Marius Leordeanu","orcid":"https://orcid.org/0000-0001-8479-8758","observed_orcids":["https://orcid.org/0000-0001-8479-8758"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marius Leordeanu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8479-8758","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.4966000020503998,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.4966000020503998,"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":0.1729000061750412,"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":0.15629999339580536,"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-segmentation","display_name":"video segmentation","score":0.8209999799728394},{"id":"https://openalex.org/keywords/graph-partitioning","display_name":"graph partitioning","score":0.8339999914169312},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"spectral clustering","score":0.9729999899864197},{"id":"https://openalex.org/keywords/principal-eigenvector","display_name":"principal eigenvector","score":0.9100000262260437},{"id":"https://openalex.org/keywords/power-iteration","display_name":"power iteration","score":0.953000009059906},{"id":"https://openalex.org/keywords/3d-convolution","display_name":"3D convolution","score":0.8920000195503235},{"id":"https://openalex.org/keywords/gpu-parallel-implementation","display_name":"GPU parallel implementation","score":0.5830000042915344},{"id":"https://openalex.org/keywords/semi-supervised-segmentation","display_name":"semi-supervised segmentation","score":0.7329999804496765}],"concepts":[{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6658371686935425},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.6636682748794556},{"id":"https://openalex.org/C180356752","wikidata":"https://www.wikidata.org/wiki/Q727035","display_name":"Adjacency matrix","level":3,"score":0.6625800728797913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6573498249053955},{"id":"https://openalex.org/C110484373","wikidata":"https://www.wikidata.org/wiki/Q264398","display_name":"Adjacency list","level":2,"score":0.5638022422790527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5495908260345459},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5173436999320984},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5077289342880249},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47885772585868835},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4760341942310333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4676971435546875},{"id":"https://openalex.org/C162443888","wikidata":"https://www.wikidata.org/wiki/Q1426504","display_name":"Power iteration","level":3,"score":0.41185474395751953},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40741217136383057},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32929906249046326},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2629462778568268},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.22552073001861572}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2953500328","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1907.02731v1","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2953500328","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1907.02731v1","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W200434350","https://openalex.org/W1999478155","https://openalex.org/W2087194382","https://openalex.org/W2102344476","https://openalex.org/W2117686912","https://openalex.org/W2117766076","https://openalex.org/W2121947440","https://openalex.org/W2132603077","https://openalex.org/W2134737843","https://openalex.org/W2161236525","https://openalex.org/W2165874743","https://openalex.org/W2166820607","https://openalex.org/W2203062554","https://openalex.org/W2218234108","https://openalex.org/W2322739735","https://openalex.org/W2470139095","https://openalex.org/W2552531400","https://openalex.org/W2564998703","https://openalex.org/W2610147486","https://openalex.org/W2724418412","https://openalex.org/W2737008123","https://openalex.org/W2740667773","https://openalex.org/W2754124089","https://openalex.org/W2799239273","https://openalex.org/W2894890793","https://openalex.org/W2895340898","https://openalex.org/W2896887415","https://openalex.org/W2899771611","https://openalex.org/W2949302831","https://openalex.org/W2955084925","https://openalex.org/W2963983744"],"related_works":["https://openalex.org/W3017335772","https://openalex.org/W4406269277","https://openalex.org/W3017083044","https://openalex.org/W2954093068","https://openalex.org/W3112761302","https://openalex.org/W4319301152","https://openalex.org/W2509313147","https://openalex.org/W2989831548","https://openalex.org/W2810393909","https://openalex.org/W1974548235"],"abstract_inverted_index":{"We":[0,27,43,133],"formulate":[1],"object":[2,41,172],"segmentation":[3,207],"in":[4,11,16,33,112,174,243],"video":[5,145],"as":[6,201],"a":[7,49,95,106,127],"graph":[8,37],"partitioning":[9],"problem":[10],"both":[12,242],"space":[13,175],"and":[14,21,51,125,176,209,245],"time,":[15],"which":[17,77,97],"nodes":[18],"are":[19],"pixels":[20],"their":[22,213],"relations":[23],"form":[24],"local":[25],"neighbourhoods.":[26],"claim":[28],"that":[29,56,100,135,184],"the":[30,39,45,58,63,67,73,86,91,113,123,152,159,179,191,203,226,232,236],"strongest":[31],"cluster":[32,47],"this":[34],"pixel":[35],"level":[36,180],"represents":[38],"salient":[40],"segmentation.":[42],"compute":[44],"main":[46],"using":[48,200,225],"novel":[50],"fast":[52,128,210],"3D":[53,110],"filtering":[54],"technique":[55],"finds":[57],"spectral":[59],"clustering":[60],"solution,":[61,214],"namely":[62],"principal":[64,92],"eigenvector":[65,93],"of":[66,94,109,144,181,205,229,235],"graph's":[68],"adjacency":[69,160],"matrix,":[70,96],"without":[71,215],"building":[72],"matrix":[74,124],"explicitly":[75],"-":[76],"would":[78],"be":[79],"intractable.":[80],"Our":[81],"method":[82],"is":[83,102,138,168],"based":[84],"on":[85,131,158,239],"power":[87,154],"iteration":[88,155],"for":[89,141,199],"finding":[90],"we":[98,221],"prove":[99],"it":[101,185,196],"equivalent":[103],"to":[104,120,170],"performing":[105],"specific":[107],"set":[108,228],"convolutions":[111],"space-time":[114],"feature":[115],"volume.":[116],"This":[117,194],"allows":[118],"us":[119],"avoid":[121],"creating":[122],"have":[126],"parallel":[129],"implementation":[130],"GPU.":[132],"show":[134],"our":[136,166],"approach":[137,167],"also":[139],"suitable":[140,198],"online":[142],"processing":[143],"streams,":[146],"while":[147],"being":[148],"much":[149],"faster":[150],"than":[151],"classical":[153],"applied":[156],"directly":[157],"matrix.":[161],"Different":[162],"from":[163],"other":[164,217],"works,":[165],"dedicated":[169],"preserving":[171],"consistency":[173],"time":[177],"at":[178,190],"pixels.":[182],"For":[183],"requires":[186],"powerful":[187],"pixel-wise":[188],"features":[189,202],"frame":[192],"level.":[193],"makes":[195],"perfectly":[197],"output":[204],"existing":[206],"algorithms":[208],"improving":[211],"over":[212,231],"any":[216],"supervision.":[218],"In":[219],"experiments,":[220],"obtain":[222],"consistent":[223],"improvement,":[224],"same":[227],"hyper-parameters,":[230],"top":[233],"state":[234],"art":[237],"methods":[238],"DAVIS-2016":[240],"dataset,":[241],"unsupervised":[244],"semi-supervised":[246],"tasks.":[247]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-07-12T00:00:00"}