{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XOOMBEP3L5BTHKU7IL3U7VHFHV","short_pith_number":"pith:XOOMBEP3","schema_version":"1.0","canonical_sha256":"bb9cc091fb5f4333aa9f42f74fd4e53d6ef07a2bb022f746763ea45ba131e055","source":{"kind":"arxiv","id":"2306.04829","version":2},"attestation_state":"computed","paper":{"title":"Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrii Zadaianchuk, Georg Martius, Maximilian Seitzer","submitted_at":"2023-06-07T23:18:14Z","abstract_excerpt":"Unsupervised video-based object-centric learning is a promising avenue to learn structured representations from large, unlabeled video collections, but previous approaches have only managed to scale to real-world datasets in restricted domains. Recently, it was shown that the reconstruction of pre-trained self-supervised features leads to object-centric representations on unconstrained real-world image datasets. Building on this approach, we propose a novel way to use such pre-trained features in the form of a temporal feature similarity loss. This loss encodes semantic and temporal correlatio"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2306.04829","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T23:18:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d7f6b86ec48a9b098f9193a645a753e9fcb335011f0288da1e53e382946722b1","abstract_canon_sha256":"9c789351aab171bae0580df3d22bbd6a5a0daa513aa4ae7548b8bccf105cf00f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:15.552045Z","signature_b64":"A3U6PUZnbpUGerPFFQKdlVkBC8lFmSP9Bo0HM2pGxaQWy+LxZIZNbpgGrAlUZjeyEo11DcH0JSoa3cNv1d1yDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb9cc091fb5f4333aa9f42f74fd4e53d6ef07a2bb022f746763ea45ba131e055","last_reissued_at":"2026-07-05T07:56:15.551543Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:15.551543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrii Zadaianchuk, Georg Martius, Maximilian Seitzer","submitted_at":"2023-06-07T23:18:14Z","abstract_excerpt":"Unsupervised video-based object-centric learning is a promising avenue to learn structured representations from large, unlabeled video collections, but previous approaches have only managed to scale to real-world datasets in restricted domains. Recently, it was shown that the reconstruction of pre-trained self-supervised features leads to object-centric representations on unconstrained real-world image datasets. Building on this approach, we propose a novel way to use such pre-trained features in the form of a temporal feature similarity loss. This loss encodes semantic and temporal correlatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04829","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.04829/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.04829","created_at":"2026-07-05T07:56:15.551600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04829v2","created_at":"2026-07-05T07:56:15.551600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04829","created_at":"2026-07-05T07:56:15.551600+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOOMBEP3L5BT","created_at":"2026-07-05T07:56:15.551600+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOOMBEP3L5BTHKU7","created_at":"2026-07-05T07:56:15.551600+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOOMBEP3","created_at":"2026-07-05T07:56:15.551600+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOOMBEP3L5BTHKU7IL3U7VHFHV","json":"https://pith.science/pith/XOOMBEP3L5BTHKU7IL3U7VHFHV.json","graph_json":"https://pith.science/api/pith-number/XOOMBEP3L5BTHKU7IL3U7VHFHV/graph.json","events_json":"https://pith.science/api/pith-number/XOOMBEP3L5BTHKU7IL3U7VHFHV/events.json","paper":"https://pith.science/paper/XOOMBEP3"},"agent_actions":{"view_html":"https://pith.science/pith/XOOMBEP3L5BTHKU7IL3U7VHFHV","download_json":"https://pith.science/pith/XOOMBEP3L5BTHKU7IL3U7VHFHV.json","view_paper":"https://pith.science/paper/XOOMBEP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04829&json=true","fetch_graph":"https://pith.science/api/pith-number/XOOMBEP3L5BTHKU7IL3U7VHFHV/graph.json","fetch_events":"https://pith.science/api/pith-number/XOOMBEP3L5BTHKU7IL3U7VHFHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOOMBEP3L5BTHKU7IL3U7VHFHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOOMBEP3L5BTHKU7IL3U7VHFHV/action/storage_attestation","attest_author":"https://pith.science/pith/XOOMBEP3L5BTHKU7IL3U7VHFHV/action/author_attestation","sign_citation":"https://pith.science/pith/XOOMBEP3L5BTHKU7IL3U7VHFHV/action/citation_signature","submit_replication":"https://pith.science/pith/XOOMBEP3L5BTHKU7IL3U7VHFHV/action/replication_record"}},"created_at":"2026-07-05T07:56:15.551600+00:00","updated_at":"2026-07-05T07:56:15.551600+00:00"}