{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AOP3DVKQBLYFPOX3WG3UCNKCDG","short_pith_number":"pith:AOP3DVKQ","schema_version":"1.0","canonical_sha256":"039fb1d5500af057bafbb1b74135421999aa0adb80b0c5accd310f6d2140abbc","source":{"kind":"arxiv","id":"1811.11325","version":4},"attestation_state":"computed","paper":{"title":"CyLKs: Unsupervised Cycle Lucas-Kanade Network for Landmark Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wentao Han, Xinshuo Weng","submitted_at":"2018-11-28T00:41:29Z","abstract_excerpt":"Across a majority of modern learning-based tracking systems, expensive annotations are needed to achieve state-of-the-art performance. In contrast, the Lucas-Kanade (LK) algorithm works well without any annotation. However, LK has a strong assumption of photometric (brightness) consistency on image intensity and is easy to drift because of large motion, occlusion, and aperture problem. To relax the assumption and alleviate the drift problem, we propose CyLKs, a data-driven way of training Lucas-Kanade in an unsupervised manner. CyLKs learns a feature transformation through CNNs, transforming t"},"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":"1811.11325","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-28T00:41:29Z","cross_cats_sorted":[],"title_canon_sha256":"a60ab9eeb98ffad13742fe0ad0bfab63babf90e7f5b6c5067b29b145aba96be9","abstract_canon_sha256":"72144fc8737fb4fe0b7ff6741cc41ce6aebaeca9455815c27569f2ef06810073"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:44.706752Z","signature_b64":"XEVqFxMY9rmnGcNdDgyruN2DlitPZux3VqfXJ0M/+ZLgVvDcW8YVUDl2ldFfTTeXxV+Dhc8z3Fp8lCkISRoHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"039fb1d5500af057bafbb1b74135421999aa0adb80b0c5accd310f6d2140abbc","last_reissued_at":"2026-05-17T23:45:44.706037Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:44.706037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CyLKs: Unsupervised Cycle Lucas-Kanade Network for Landmark Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wentao Han, Xinshuo Weng","submitted_at":"2018-11-28T00:41:29Z","abstract_excerpt":"Across a majority of modern learning-based tracking systems, expensive annotations are needed to achieve state-of-the-art performance. In contrast, the Lucas-Kanade (LK) algorithm works well without any annotation. However, LK has a strong assumption of photometric (brightness) consistency on image intensity and is easy to drift because of large motion, occlusion, and aperture problem. To relax the assumption and alleviate the drift problem, we propose CyLKs, a data-driven way of training Lucas-Kanade in an unsupervised manner. CyLKs learns a feature transformation through CNNs, transforming t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11325","kind":"arxiv","version":4},"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":"1811.11325","created_at":"2026-05-17T23:45:44.706162+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.11325v4","created_at":"2026-05-17T23:45:44.706162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11325","created_at":"2026-05-17T23:45:44.706162+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOP3DVKQBLYF","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOP3DVKQBLYFPOX3","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOP3DVKQ","created_at":"2026-05-18T12:32:13.499390+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/AOP3DVKQBLYFPOX3WG3UCNKCDG","json":"https://pith.science/pith/AOP3DVKQBLYFPOX3WG3UCNKCDG.json","graph_json":"https://pith.science/api/pith-number/AOP3DVKQBLYFPOX3WG3UCNKCDG/graph.json","events_json":"https://pith.science/api/pith-number/AOP3DVKQBLYFPOX3WG3UCNKCDG/events.json","paper":"https://pith.science/paper/AOP3DVKQ"},"agent_actions":{"view_html":"https://pith.science/pith/AOP3DVKQBLYFPOX3WG3UCNKCDG","download_json":"https://pith.science/pith/AOP3DVKQBLYFPOX3WG3UCNKCDG.json","view_paper":"https://pith.science/paper/AOP3DVKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.11325&json=true","fetch_graph":"https://pith.science/api/pith-number/AOP3DVKQBLYFPOX3WG3UCNKCDG/graph.json","fetch_events":"https://pith.science/api/pith-number/AOP3DVKQBLYFPOX3WG3UCNKCDG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOP3DVKQBLYFPOX3WG3UCNKCDG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOP3DVKQBLYFPOX3WG3UCNKCDG/action/storage_attestation","attest_author":"https://pith.science/pith/AOP3DVKQBLYFPOX3WG3UCNKCDG/action/author_attestation","sign_citation":"https://pith.science/pith/AOP3DVKQBLYFPOX3WG3UCNKCDG/action/citation_signature","submit_replication":"https://pith.science/pith/AOP3DVKQBLYFPOX3WG3UCNKCDG/action/replication_record"}},"created_at":"2026-05-17T23:45:44.706162+00:00","updated_at":"2026-05-17T23:45:44.706162+00:00"}