{"authors":[{"id":null,"fullName":"Manasyan, A.","name":"A.","surname":"Manasyan","rank":1,"pid":null},{"id":null,"fullName":"Seitzer, M.","name":"M.","surname":"Seitzer","rank":2,"pid":null},{"id":null,"fullName":"Radovic, F.","name":"F.","surname":"Radovic","rank":3,"pid":null},{"id":null,"fullName":"Martius, Georg","name":"Georg","surname":"Martius","rank":4,"pid":null},{"id":null,"fullName":"Zadaianchuk, A.","name":"A.","surname":"Zadaianchuk","rank":5,"pid":null}],"openAccessColor":null,"publiclyFunded":false,"eoscIfGuidelines":null,"type":"publication","language":{"code":"und","label":"Undetermined"},"countries":[{"code":"NL","label":"Netherlands","provenance":null}],"subjects":[{"subject":{"scheme":"keyword","value":"FOS: Computer and information sciences"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Machine Learning"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Robotics"},"provenance":null},{"subject":{"scheme":"keyword","value":"Artificial Intelligence (cs.AI)"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Artificial Intelligence"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Vision and Pattern Recognition (cs.CV)"},"provenance":null},{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Computer Vision and Pattern Recognition"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"Robotics (cs.RO)"},"provenance":null},{"subject":{"scheme":"keyword","value":"Machine Learning (cs.LG)"},"provenance":null}],"mainTitle":"Temporally Consistent Object-Centric Learning by Contrasting Slots","subTitle":null,"descriptions":["Unsupervised object-centric learning from videos is a promising approach to extract structured representations from large, unlabeled collections of videos. To support downstream tasks like autonomous control, these representations must be both compositional and temporally consistent. Existing approaches based on recurrent processing often lack long-term stability across frames because their training objective does not enforce temporal consistency. In this work, we introduce a novel object-level temporal contrastive loss for video object-centric models that explicitly promotes temporal consistency. Our method significantly improves the temporal consistency of the learned object-centric representations, yielding more reliable video decompositions that facilitate challenging downstream tasks such as unsupervised object dynamics prediction. Furthermore, the inductive bias added by our loss strongly improves object discovery, leading to state-of-the-art results on both synthetic and real-world datasets, outperforming even weakly-supervised methods that leverage motion masks as additional cues.","Published at CVPR 2025"],"publicationDate":"2025-06-10","publisher":"IEEE","embargoEndDate":"2024-12-01","sources":["Crossref"],"formats":null,"contributors":null,"coverages":null,"bestAccessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":{"name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","issnPrinted":null,"issnOnline":null,"issnLinking":null,"ep":"5411","iss":null,"sp":"5401","vol":null,"edition":null,"conferencePlace":null,"conferenceDate":null},"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::e70a121bbfb6d78b187a9bdf313780c3","originalIds":["10.1109/cvpr52734.2025.00508","50|doiboost____|fa7ee2e9e63133b34a1ad086a1205beb","50|datacite____::e70a121bbfb6d78b187a9bdf313780c3","10.48550/arxiv.2412.14295","50|od________18::3f70f1942d229a1cd830f54700bfe40d","oai:arXiv.org:2412.14295","50|dblp________::ab9c282666628711b92ff546cab8e5d7","50|dblp________::dea145f862e09ba77d4f401ea883f8be","oai:dare.uva.nl:openaire_cris_publications/aec3fccd-cedb-4ace-a486-23e2b28cc077","50|dris___01178::c37d7d24131d987fe19fe2113bfae546"],"pids":[{"scheme":"doi","value":"10.1109/cvpr52734.2025.00508"},{"scheme":"doi","value":"10.48550/arxiv.2412.14295"},{"scheme":"arXiv","value":"2412.14295"},{"scheme":"handle","value":"11245.1/aec3fccd-cedb-4ace-a486-23e2b28cc077"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":0.0,"influence":2.1746283E-9,"popularity":2.2497804E-9,"impulse":0.0,"citationClass":"C5","influenceClass":"C5","impulseClass":"C5","popularityClass":"C5"}},"projects":[{"id":"corda__h2020::d625d0cbad35029342e74be852d55f35","code":"950086","acronym":"EVA","title":"Expectational Visual Artificial Intelligence","funder":"European Commission","pids":[{"scheme":"doi","value":"10.3030/950086"}]},{"id":"corda_____he::96ef8b99ae60c1fe76de7f7d165e8073","code":"101045454","acronym":"REAL-RL","title":"Model-based Reinforcement Learning for Versatile Robots in the Real World","funder":"European Commission","pids":[{"scheme":"doi","value":"10.3030/101045454"}]}],"organizations":[{"legalName":"University of Tübingen","acronym":"University of Tübingen","id":"openorgs____::ca58585cd878d3df6de7871d6d5a6e9e","pids":[{"scheme":"mag_id","value":"8087733"},{"scheme":"ROR","value":"https://ror.org/03a1kwz48"},{"scheme":"fundref","value":"501100002346"},{"scheme":"FundRef","value":"501100002346"},{"scheme":"fundref","value":"501100002345"},{"scheme":"FundRef","value":"501100009397"},{"scheme":"GRID","value":"grid.10392.39"},{"scheme":"OrgRef","value":"262301"},{"scheme":"FundRef","value":"501100002345"},{"scheme":"ISNI","value":"0000000121901447"},{"scheme":"Wikidata","value":"Q153978"},{"scheme":"fundref","value":"501100009397"},{"scheme":"wikidata","value":"Q153978"}],"countries":[{"code":"DE","label":"Germany"}],"websiteurl":"https://www.uni-tuebingen.de/en/university.html"},{"legalName":"University of Amsterdam","acronym":"UvA","id":"openorgs____::58f65ed1ce3c9166e9c5f939bfdbf83a","pids":[{"scheme":"Wikidata","value":"Q214341"},{"scheme":"GRID","value":"grid.7177.6"},{"scheme":"ROR","value":"https://ror.org/04dkp9463"},{"scheme":"FundRef","value":"501100019541"},{"scheme":"RRID","value":"RRID:nlx_19684"},{"scheme":"wikidata","value":"Q56648966"},{"scheme":"OrgRef","value":"546160"},{"scheme":"wikidata","value":"Q2017571"},{"scheme":"Wikidata","value":"Q56648966"},{"scheme":"RRID","value":"RRID:SCR_002385"},{"scheme":"ISNI","value":"0000000084992262"},{"scheme":"OrgReg","value":"NL0001"},{"scheme":"FundRef","value":"501100001827"},{"scheme":"OrgRef","value":"36945751"},{"scheme":"Wikidata","value":"Q2017571"},{"scheme":"wikidata","value":"Q214341"},{"scheme":"fundref","value":"501100019541"},{"scheme":"mag_id","value":"887064364"},{"scheme":"fundref","value":"501100001827"},{"scheme":"PIC","value":"999985708"}],"countries":[{"code":"NL","label":"Netherlands"}],"websiteurl":"http://www.uva.nl/en/home"}],"communities":[{"code":"netherlands","label":"Netherlands Research Portal","provenance":null}],"collectedFrom":[{"key":"openaire____::9e3be59865b2c1c335d32dae2fe7b254","value":"Datacite"},{"key":"openaire____::081b82f96300b6a6e3d282bad31cb6e2","value":"Crossref"},{"key":"eurocrisdris::6843472268136d4e2321160af2ddf287","value":"Universiteit van Amsterdam (UvA) Institutional Repository UvA-DARE"},{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"},{"key":"opendoar____::6f4922f45568161a8cdf4ad2299f6d23","value":"arXiv.org e-Print Archive"}],"instances":[{"pids":[{"scheme":"doi","value":"10.1109/cvpr52734.2025.00508"}],"license":"STM Policy #29","accessRight":{"code":"c_14cb","label":"CLOSED","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Article","urls":["https://doi.org/10.1109/cvpr52734.2025.00508"],"publicationDate":"2025-06-10","refereed":"peerReviewed","hostedBy":{"key":"openaire____::55045bd2a65019fd8e6741a755395c8c","value":"Unknown Repository"},"collectedFrom":{"key":"openaire____::081b82f96300b6a6e3d282bad31cb6e2","value":"Crossref"}},{"pids":[{"scheme":"doi","value":"10.48550/arxiv.2412.14295"}],"license":"arXiv Non-Exclusive Distribution","type":"Article","urls":["https://dx.doi.org/10.48550/arxiv.2412.14295"],"publicationDate":"2024-01-01","refereed":"nonPeerReviewed","hostedBy":{"key":"openaire____::55045bd2a65019fd8e6741a755395c8c","value":"Unknown Repository"},"collectedFrom":{"key":"openaire____::9e3be59865b2c1c335d32dae2fe7b254","value":"Datacite"}},{"pids":[{"scheme":"arXiv","value":"2412.14295"}],"accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Preprint","urls":["http://arxiv.org/abs/2412.14295"],"publicationDate":"2024-12-18","refereed":"nonPeerReviewed","hostedBy":{"key":"opendoar____::6f4922f45568161a8cdf4ad2299f6d23","value":"arXiv.org e-Print Archive"},"collectedFrom":{"key":"opendoar____::6f4922f45568161a8cdf4ad2299f6d23","value":"arXiv.org e-Print Archive"}},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1109/cvpr52734.2025.00508"}],"type":"Conference object","urls":["https://dblp.org/rec/conf/cvpr/ManasyanSRMZ25.html","https://doi.org/10.1109/CVPR52734.2025.00508"],"refereed":"nonPeerReviewed","hostedBy":{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"},"collectedFrom":{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"}},{"alternateIdentifiers":[{"scheme":"doi","value":"10.48550/arxiv.2412.14295"}],"type":"Preprint","urls":["https://dblp.org/rec/journals/corr/abs-2412-14295.html","https://doi.org/10.48550/arXiv.2412.14295"],"publicationDate":"2024-01-01","refereed":"nonPeerReviewed","hostedBy":{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"},"collectedFrom":{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"}},{"pids":[{"scheme":"handle","value":"11245.1/aec3fccd-cedb-4ace-a486-23e2b28cc077"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.48550/arxiv.2412.14295"}],"license":"taverne","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Conference object","urls":["https://hdl.handle.net/11245.1/aec3fccd-cedb-4ace-a486-23e2b28cc077","https://doi.org/10.48550/arXiv.2412.14295","https://handle.uba.uva.nl/personal/pure/en/publications/temporally-consistent-objectcentric-learning-by-contrasting-slots(aec3fccd-cedb-4ace-a486-23e2b28cc077).html"],"publicationDate":"2025-01-01","refereed":"nonPeerReviewed","hostedBy":{"key":"eurocrisdris::6843472268136d4e2321160af2ddf287","value":"Universiteit van Amsterdam (UvA) Institutional Repository UvA-DARE"},"collectedFrom":{"key":"eurocrisdris::6843472268136d4e2321160af2ddf287","value":"Universiteit van Amsterdam (UvA) Institutional Repository UvA-DARE"}}],"links":[{"header":{"relationType":"resultProject","relationClass":"isProducedBy","relatedIdentifier":"corda__h2020::d625d0cbad35029342e74be852d55f35","relatedRecordType":"project","relationProvenance":"iis","trust":"0.897"},"collectedfrom":[{"dsId":"openaire____::a55eb91348674d853191f4f4fd73d078","dsName":"CORDA - COmmon Research DAta Warehouse - Horizon 2020"}],"projectTitle":"Expectational Visual Artificial Intelligence","code":"950086","funding":{"funder":{"id":"ec__________::EC","shortname":"EC","name":"European Commission","jurisdiction":{"code":"EU","label":"European Union"},"pid":null},"level0":{"id":"ec__________::EC::H2020","description":"Horizon 2020 Framework Programme","name":"H2020"},"level1":{"id":"ec__________::EC::H2020::ERC","description":"European Research Council","name":"ERC"},"level2":{"id":"ec__________::EC::H2020::ERC::ERC-STG","description":"Starting Grant","name":"ERC-STG"}},"startDate":"2020-12-01","endDate":"2025-11-30"},{"header":{"relationType":"resultProject","relationClass":"isProducedBy","relatedIdentifier":"corda_____he::96ef8b99ae60c1fe76de7f7d165e8073","relatedRecordType":"project","relationProvenance":"iis","trust":"0.7348"},"collectedfrom":[{"dsId":"openaire____::3f264f93cf3b0cfc4ede188a6300455c","dsName":"CORDA - COmmon Research DAta Warehouse - Horizon Europe"}],"projectTitle":"Model-based Reinforcement Learning for Versatile Robots in the Real World","code":"101045454","funding":{"funder":{"id":"ec__________::EC","shortname":"EC","name":"European Commission","jurisdiction":{"code":"EU","label":"European Union"},"pid":null},"level0":{"id":"ec__________::EC::HE","description":"Horizon Europe Framework Programme","name":"HE"},"level1":{"id":"ec__________::EC::HE::HORIZON-AG","description":"HORIZON Action Grant Budget-Based","name":"HORIZON-AG"},"level2":{"id":null,"description":null,"name":null}},"startDate":"2023-01-01","endDate":"2027-12-31"}],"otherTitles":null,"inDiamondJournal":false,"green":true,"isGreen":true,"isInDiamondJournal":false}