{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YN3FBX32WIPJ6P4PLYX26VN6U7","short_pith_number":"pith:YN3FBX32","schema_version":"1.0","canonical_sha256":"c37650df7ab21e9f3f8f5e2faf55bea7fb620ce16c25fd048d44cf65cd43ed4c","source":{"kind":"arxiv","id":"1806.09594","version":2},"attestation_state":"computed","paper":{"title":"Tracking Emerges by Colorizing Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG","cs.MM","cs.RO"],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Alireza Fathi, Carl Vondrick, Kevin Murphy, Sergio Guadarrama","submitted_at":"2018-06-25T17:44:40Z","abstract_excerpt":"We use large amounts of unlabeled video to learn models for visual tracking without manual human supervision. We leverage the natural temporal coherency of color to create a model that learns to colorize gray-scale videos by copying colors from a reference frame. Quantitative and qualitative experiments suggest that this task causes the model to automatically learn to track visual regions. Although the model is trained without any ground-truth labels, our method learns to track well enough to outperform the latest methods based on optical flow. Moreover, our results suggest that failures to tr"},"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":"1806.09594","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-25T17:44:40Z","cross_cats_sorted":["cs.GR","cs.LG","cs.MM","cs.RO"],"title_canon_sha256":"91019568e4700a1ed0c4a081bf99d964258b125750cce4b45827770fbc2e2aa1","abstract_canon_sha256":"d2dcc633ec677abedf2a6a562070d7d2f8bd410b7a3bb19ef232df8681f3d3cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:37.492897Z","signature_b64":"R+WAlk+7bEI1JG2Vpa75Aiqrs0imnw+VB9BxrYCY8w0h8ylen7+YX7GuJl46NwOaxHIJMKO+YEoYl4Sg5byHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c37650df7ab21e9f3f8f5e2faf55bea7fb620ce16c25fd048d44cf65cd43ed4c","last_reissued_at":"2026-05-18T00:09:37.492250Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:37.492250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tracking Emerges by Colorizing Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG","cs.MM","cs.RO"],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Alireza Fathi, Carl Vondrick, Kevin Murphy, Sergio Guadarrama","submitted_at":"2018-06-25T17:44:40Z","abstract_excerpt":"We use large amounts of unlabeled video to learn models for visual tracking without manual human supervision. We leverage the natural temporal coherency of color to create a model that learns to colorize gray-scale videos by copying colors from a reference frame. Quantitative and qualitative experiments suggest that this task causes the model to automatically learn to track visual regions. Although the model is trained without any ground-truth labels, our method learns to track well enough to outperform the latest methods based on optical flow. Moreover, our results suggest that failures to tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.09594","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":""},"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":"1806.09594","created_at":"2026-05-18T00:09:37.492379+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.09594v2","created_at":"2026-05-18T00:09:37.492379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.09594","created_at":"2026-05-18T00:09:37.492379+00:00"},{"alias_kind":"pith_short_12","alias_value":"YN3FBX32WIPJ","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YN3FBX32WIPJ6P4P","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YN3FBX32","created_at":"2026-05-18T12:33:04.347982+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/YN3FBX32WIPJ6P4PLYX26VN6U7","json":"https://pith.science/pith/YN3FBX32WIPJ6P4PLYX26VN6U7.json","graph_json":"https://pith.science/api/pith-number/YN3FBX32WIPJ6P4PLYX26VN6U7/graph.json","events_json":"https://pith.science/api/pith-number/YN3FBX32WIPJ6P4PLYX26VN6U7/events.json","paper":"https://pith.science/paper/YN3FBX32"},"agent_actions":{"view_html":"https://pith.science/pith/YN3FBX32WIPJ6P4PLYX26VN6U7","download_json":"https://pith.science/pith/YN3FBX32WIPJ6P4PLYX26VN6U7.json","view_paper":"https://pith.science/paper/YN3FBX32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.09594&json=true","fetch_graph":"https://pith.science/api/pith-number/YN3FBX32WIPJ6P4PLYX26VN6U7/graph.json","fetch_events":"https://pith.science/api/pith-number/YN3FBX32WIPJ6P4PLYX26VN6U7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YN3FBX32WIPJ6P4PLYX26VN6U7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YN3FBX32WIPJ6P4PLYX26VN6U7/action/storage_attestation","attest_author":"https://pith.science/pith/YN3FBX32WIPJ6P4PLYX26VN6U7/action/author_attestation","sign_citation":"https://pith.science/pith/YN3FBX32WIPJ6P4PLYX26VN6U7/action/citation_signature","submit_replication":"https://pith.science/pith/YN3FBX32WIPJ6P4PLYX26VN6U7/action/replication_record"}},"created_at":"2026-05-18T00:09:37.492379+00:00","updated_at":"2026-05-18T00:09:37.492379+00:00"}