{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WCQ7DCALOCABUWA47VILHBIVSL","short_pith_number":"pith:WCQ7DCAL","schema_version":"1.0","canonical_sha256":"b0a1f1880b70801a581cfd50b3851592e10427abc15fdefde49817ab41a9a853","source":{"kind":"arxiv","id":"1702.02295","version":2},"attestation_state":"computed","paper":{"title":"Guided Optical Flow Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander G. Hauptmann, Shawn Newsam, Yi Zhu, Zhenzhong Lan","submitted_at":"2017-02-08T05:42:09Z","abstract_excerpt":"We study the unsupervised learning of CNNs for optical flow estimation using proxy ground truth data. Supervised CNNs, due to their immense learning capacity, have shown superior performance on a range of computer vision problems including optical flow prediction. They however require the ground truth flow which is usually not accessible except on limited synthetic data. Without the guidance of ground truth optical flow, unsupervised CNNs often perform worse as they are naturally ill-conditioned. We therefore propose a novel framework in which proxy ground truth data generated from classical a"},"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":"1702.02295","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-08T05:42:09Z","cross_cats_sorted":[],"title_canon_sha256":"43357671ca5f227cf7bbf34eba77f7d46647b04986f212016221941774d16c18","abstract_canon_sha256":"2dbd8007dc7e1ffd63eb65d444d2a44c33deaa3c425406f3a7aa4f41e1d7d1af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:07.421989Z","signature_b64":"lFFx6Dxec9VeAq44+c3CWHtLC17irSfnDWuby/J6Bh/3exQPG5M1v1tPZsRTlV5UE6J+ZTYBdlR/j9WX5CkNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0a1f1880b70801a581cfd50b3851592e10427abc15fdefde49817ab41a9a853","last_reissued_at":"2026-05-18T00:41:07.421393Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:07.421393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guided Optical Flow Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander G. Hauptmann, Shawn Newsam, Yi Zhu, Zhenzhong Lan","submitted_at":"2017-02-08T05:42:09Z","abstract_excerpt":"We study the unsupervised learning of CNNs for optical flow estimation using proxy ground truth data. Supervised CNNs, due to their immense learning capacity, have shown superior performance on a range of computer vision problems including optical flow prediction. They however require the ground truth flow which is usually not accessible except on limited synthetic data. Without the guidance of ground truth optical flow, unsupervised CNNs often perform worse as they are naturally ill-conditioned. We therefore propose a novel framework in which proxy ground truth data generated from classical a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.02295","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":"1702.02295","created_at":"2026-05-18T00:41:07.421473+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.02295v2","created_at":"2026-05-18T00:41:07.421473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.02295","created_at":"2026-05-18T00:41:07.421473+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCQ7DCALOCAB","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCQ7DCALOCABUWA4","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCQ7DCAL","created_at":"2026-05-18T12:31:53.515858+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/WCQ7DCALOCABUWA47VILHBIVSL","json":"https://pith.science/pith/WCQ7DCALOCABUWA47VILHBIVSL.json","graph_json":"https://pith.science/api/pith-number/WCQ7DCALOCABUWA47VILHBIVSL/graph.json","events_json":"https://pith.science/api/pith-number/WCQ7DCALOCABUWA47VILHBIVSL/events.json","paper":"https://pith.science/paper/WCQ7DCAL"},"agent_actions":{"view_html":"https://pith.science/pith/WCQ7DCALOCABUWA47VILHBIVSL","download_json":"https://pith.science/pith/WCQ7DCALOCABUWA47VILHBIVSL.json","view_paper":"https://pith.science/paper/WCQ7DCAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.02295&json=true","fetch_graph":"https://pith.science/api/pith-number/WCQ7DCALOCABUWA47VILHBIVSL/graph.json","fetch_events":"https://pith.science/api/pith-number/WCQ7DCALOCABUWA47VILHBIVSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCQ7DCALOCABUWA47VILHBIVSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCQ7DCALOCABUWA47VILHBIVSL/action/storage_attestation","attest_author":"https://pith.science/pith/WCQ7DCALOCABUWA47VILHBIVSL/action/author_attestation","sign_citation":"https://pith.science/pith/WCQ7DCALOCABUWA47VILHBIVSL/action/citation_signature","submit_replication":"https://pith.science/pith/WCQ7DCALOCABUWA47VILHBIVSL/action/replication_record"}},"created_at":"2026-05-18T00:41:07.421473+00:00","updated_at":"2026-05-18T00:41:07.421473+00:00"}