{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KSFSPMD37S4ZGEZVTCHHC2LIZT","short_pith_number":"pith:KSFSPMD3","schema_version":"1.0","canonical_sha256":"548b27b07bfcb9931335988e716968cccc1d51b37fc7a39749cdd1cb305fbe81","source":{"kind":"arxiv","id":"1711.07837","version":1},"attestation_state":"computed","paper":{"title":"UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junhwa Hur, Simon Meister, Stefan Roth","submitted_at":"2017-11-21T15:19:26Z","abstract_excerpt":"In the era of end-to-end deep learning, many advances in computer vision are driven by large amounts of labeled data. In the optical flow setting, however, obtaining dense per-pixel ground truth for real scenes is difficult and thus such data is rare. Therefore, recent end-to-end convolutional networks for optical flow rely on synthetic datasets for supervision, but the domain mismatch between training and test scenarios continues to be a challenge. Inspired by classical energy-based optical flow methods, we design an unsupervised loss based on occlusion-aware bidirectional flow estimation and"},"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":"1711.07837","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-21T15:19:26Z","cross_cats_sorted":[],"title_canon_sha256":"89124318c08363a4e4938b4db78cdebb782b3eeb74e6910f8d22b143f191f980","abstract_canon_sha256":"58da7f164119dbd91bfbe5fcb7e2d932b213d18503075cd7612d904e7f07bbdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:56.384748Z","signature_b64":"+4lsykbX6C6u46hIIrbS6zoHkYg+ftD0BKjBK0CoT8rrgMOjYhinXUSkF+Qm2BcI/2PI3aI20K/GK7PqdDfUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"548b27b07bfcb9931335988e716968cccc1d51b37fc7a39749cdd1cb305fbe81","last_reissued_at":"2026-05-18T00:29:56.384303Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:56.384303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junhwa Hur, Simon Meister, Stefan Roth","submitted_at":"2017-11-21T15:19:26Z","abstract_excerpt":"In the era of end-to-end deep learning, many advances in computer vision are driven by large amounts of labeled data. In the optical flow setting, however, obtaining dense per-pixel ground truth for real scenes is difficult and thus such data is rare. Therefore, recent end-to-end convolutional networks for optical flow rely on synthetic datasets for supervision, but the domain mismatch between training and test scenarios continues to be a challenge. Inspired by classical energy-based optical flow methods, we design an unsupervised loss based on occlusion-aware bidirectional flow estimation and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.07837","kind":"arxiv","version":1},"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":"1711.07837","created_at":"2026-05-18T00:29:56.384384+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.07837v1","created_at":"2026-05-18T00:29:56.384384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.07837","created_at":"2026-05-18T00:29:56.384384+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSFSPMD37S4Z","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSFSPMD37S4ZGEZV","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSFSPMD3","created_at":"2026-05-18T12:31:28.150371+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/KSFSPMD37S4ZGEZVTCHHC2LIZT","json":"https://pith.science/pith/KSFSPMD37S4ZGEZVTCHHC2LIZT.json","graph_json":"https://pith.science/api/pith-number/KSFSPMD37S4ZGEZVTCHHC2LIZT/graph.json","events_json":"https://pith.science/api/pith-number/KSFSPMD37S4ZGEZVTCHHC2LIZT/events.json","paper":"https://pith.science/paper/KSFSPMD3"},"agent_actions":{"view_html":"https://pith.science/pith/KSFSPMD37S4ZGEZVTCHHC2LIZT","download_json":"https://pith.science/pith/KSFSPMD37S4ZGEZVTCHHC2LIZT.json","view_paper":"https://pith.science/paper/KSFSPMD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.07837&json=true","fetch_graph":"https://pith.science/api/pith-number/KSFSPMD37S4ZGEZVTCHHC2LIZT/graph.json","fetch_events":"https://pith.science/api/pith-number/KSFSPMD37S4ZGEZVTCHHC2LIZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSFSPMD37S4ZGEZVTCHHC2LIZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSFSPMD37S4ZGEZVTCHHC2LIZT/action/storage_attestation","attest_author":"https://pith.science/pith/KSFSPMD37S4ZGEZVTCHHC2LIZT/action/author_attestation","sign_citation":"https://pith.science/pith/KSFSPMD37S4ZGEZVTCHHC2LIZT/action/citation_signature","submit_replication":"https://pith.science/pith/KSFSPMD37S4ZGEZVTCHHC2LIZT/action/replication_record"}},"created_at":"2026-05-18T00:29:56.384384+00:00","updated_at":"2026-05-18T00:29:56.384384+00:00"}