{"id":"https://openalex.org/W3134801614","doi":"https://doi.org/10.1109/icip42928.2021.9506062","title":"Self-Supervision By Prediction For Object Discovery In Videos","display_name":"Self-Supervision By Prediction For Object Discovery In Videos","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3134801614","doi":"https://doi.org/10.1109/icip42928.2021.9506062","mag":"3134801614"},"language":"en","primary_location":{"id":"doi:10.1109/icip42928.2021.9506062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.05669","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027933458","display_name":"Beril Be\u015fb\u0131nar","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Beril Besbinar","raw_affiliation_strings":["Signal Processing Laboratory (LTS4) École Polytechnique Fédérale de Lausanne (EPFL)","\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Processing Laboratory (LTS4) École Polytechnique Fédérale de Lausanne (EPFL)","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne,","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000947076","display_name":"Pascal Frossard","orcid":"https://orcid.org/0000-0002-4010-714X"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Pascal Frossard","raw_affiliation_strings":["Signal Processing Laboratory (LTS4) École Polytechnique Fédérale de Lausanne (EPFL)","\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Processing Laboratory (LTS4) École Polytechnique Fédérale de Lausanne (EPFL)","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5124864"],"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":"2","issue":null,"first_page":"1509","last_page":"1513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8348364233970642},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7066978812217712},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.703339159488678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6961913108825684},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.659116804599762},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6398512125015259},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5821045637130737},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.569379448890686},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5588797926902771},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5542558431625366},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5426117181777954},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46714895963668823},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.42145439982414246},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41808751225471497},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07072639465332031}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8348364233970642},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7066978812217712},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.703339159488678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6961913108825684},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.659116804599762},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6398512125015259},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5821045637130737},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.569379448890686},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5588797926902771},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5542558431625366},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5426117181777954},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46714895963668823},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.42145439982414246},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41808751225471497},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07072639465332031},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icip42928.2021.9506062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.05669","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.05669","pdf_url":"https://arxiv.org/pdf/2103.05669","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3134801614","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2103.05669","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:infoscience.epfl.ch:295855","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/295855","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"conference proceedings"},{"id":"doi:10.48550/arxiv.2103.05669","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.05669","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/2js3-x582","is_oa":true,"landing_page_url":"https://doi.org/10.17023/2js3-x582","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.05669","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.05669","pdf_url":"https://arxiv.org/pdf/2103.05669","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1485009520","https://openalex.org/W1522301498","https://openalex.org/W1560408190","https://openalex.org/W1568514080","https://openalex.org/W1930563420","https://openalex.org/W2120606367","https://openalex.org/W2194775991","https://openalex.org/W2248556341","https://openalex.org/W2401640538","https://openalex.org/W2414711238","https://openalex.org/W2470142083","https://openalex.org/W2586480386","https://openalex.org/W2615413256","https://openalex.org/W2626778328","https://openalex.org/W2738136547","https://openalex.org/W2749658623","https://openalex.org/W2786615588","https://openalex.org/W2796303840","https://openalex.org/W2798788386","https://openalex.org/W2904099109","https://openalex.org/W2918222882","https://openalex.org/W2919112510","https://openalex.org/W2948412951","https://openalex.org/W2962784289","https://openalex.org/W2963045453","https://openalex.org/W2963092440","https://openalex.org/W2963402657","https://openalex.org/W2963547393","https://openalex.org/W2963629403","https://openalex.org/W2963657860","https://openalex.org/W2964213104","https://openalex.org/W2964303162","https://openalex.org/W2989705138","https://openalex.org/W2989708447","https://openalex.org/W2991019415","https://openalex.org/W2991327061","https://openalex.org/W2997571320","https://openalex.org/W3005844337","https://openalex.org/W3028924880","https://openalex.org/W3035540643","https://openalex.org/W3037581554","https://openalex.org/W3037784242","https://openalex.org/W3102427165","https://openalex.org/W6618372016","https://openalex.org/W6631190155","https://openalex.org/W6634221342","https://openalex.org/W6691096134","https://openalex.org/W6712884540","https://openalex.org/W6713563955","https://openalex.org/W6728805014","https://openalex.org/W6738465933","https://openalex.org/W6742720488","https://openalex.org/W6747885307","https://openalex.org/W6752365561","https://openalex.org/W6759669191","https://openalex.org/W6759977823","https://openalex.org/W6763239785","https://openalex.org/W6769570503","https://openalex.org/W6770086194","https://openalex.org/W6779689074","https://openalex.org/W6779809370"],"related_works":["https://openalex.org/W3195914228","https://openalex.org/W2952355813","https://openalex.org/W3158723897","https://openalex.org/W2907424612","https://openalex.org/W3015167968","https://openalex.org/W3194728812","https://openalex.org/W2766653014","https://openalex.org/W3046844194","https://openalex.org/W2540456849","https://openalex.org/W3137275046","https://openalex.org/W2963441581","https://openalex.org/W2906748551","https://openalex.org/W2895573355","https://openalex.org/W3098970982","https://openalex.org/W3047336584","https://openalex.org/W2612576664","https://openalex.org/W2520761760","https://openalex.org/W3167221503","https://openalex.org/W3173123194","https://openalex.org/W2944059049"],"abstract_inverted_index":{"Despite":[0],"their":[1],"irresistible":[2],"success,":[3],"deep":[4],"learning":[5],"algorithms":[6],"still":[7],"heavily":[8],"rely":[9],"on":[10],"annotated":[11],"data,":[12],"and":[13,52,62,66,81],"unsupervised":[14],"settings":[15],"pose":[16],"many":[17],"challenges,":[18],"such":[19],"as":[20],"finding":[21],"the":[22,43,69,72,92],"right":[23],"inductive":[24],"bias":[25],"in":[26],"diverse":[27],"scenarios.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,86],"propose":[33],"an":[34],"object-centric":[35,112],"model":[36],"for":[37,46,68],"image":[38],"sequence":[39],"representation":[40,51],"that":[41,103],"uses":[42],"prediction":[44],"task":[45],"self-supervision.":[47],"By":[48],"disentangling":[49],"object":[50,84],"motion":[53],"dynamics,":[54],"our":[55,88,104],"novel":[56],"compositional":[57],"structure":[58],"explicitly":[59],"handles":[60],"occlusion":[61],"inpaints":[63],"inferred":[64],"objects":[65],"background":[67],"composition":[70],"of":[71,94],"predicted":[73],"frame.":[74],"Using":[75],"auxiliary":[76],"losses":[77],"to":[78],"promote":[79],"spatially":[80],"temporally":[82],"consistent":[83],"representations,":[85],"train":[87],"self-supervised":[89],"framework":[90],"without":[91],"help":[93],"any":[95],"annotation":[96],"or":[97],"pretrained":[98],"network.":[99],"Initial":[100],"experiments":[101],"confirm":[102],"new":[105],"pipeline":[106],"is":[107],"a":[108],"promising":[109],"step":[110],"towards":[111],"video":[113],"prediction.":[114]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-03-15T00:00:00"}