{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:QPV73BSGZWRCR3EAPLSH3X7P3E","short_pith_number":"pith:QPV73BSG","schema_version":"1.0","canonical_sha256":"83ebfd8646cda228ec807ae47ddfefd92e041f6b05ad78f5b1f8d60790b69475","source":{"kind":"arxiv","id":"1612.00979","version":1},"attestation_state":"computed","paper":{"title":"Semi-supervised learning of deep metrics for stereo reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"Anton Ivanov, Francois Fleuret, Stepan Tulyakov","submitted_at":"2016-12-03T16:09:32Z","abstract_excerpt":"Deep-learning metrics have recently demonstrated extremely good performance to match image patches for stereo reconstruction. However, training such metrics requires large amount of labeled stereo images, which can be difficult or costly to collect for certain applications. The main contribution of our work is a new semi-supervised method for learning deep metrics from unlabeled stereo images, given coarse information about the scenes and the optical system. Our method alternatively optimizes the metric with a standard stochastic gradient descent, and applies stereo constraints to regularize i"},"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":"1612.00979","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-03T16:09:32Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"8007b5d20a38b811f56d2e3116399454c167dcee4c57e3503ebd2de1207cfc37","abstract_canon_sha256":"b8677c80b56b277fad1f0c2cf610270a148855a617cb3c32b918dd9f7bca4d19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:53.664724Z","signature_b64":"NzWeE8uF7EXKFaIt67U4jsZh1mE+/u7BeAe6I0D6VZ8d0gRZ/ywUxwQwskBZqWKuc+haWruAv0BaS4rLSqWYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83ebfd8646cda228ec807ae47ddfefd92e041f6b05ad78f5b1f8d60790b69475","last_reissued_at":"2026-05-18T00:55:53.663906Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:53.663906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-supervised learning of deep metrics for stereo reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"Anton Ivanov, Francois Fleuret, Stepan Tulyakov","submitted_at":"2016-12-03T16:09:32Z","abstract_excerpt":"Deep-learning metrics have recently demonstrated extremely good performance to match image patches for stereo reconstruction. However, training such metrics requires large amount of labeled stereo images, which can be difficult or costly to collect for certain applications. The main contribution of our work is a new semi-supervised method for learning deep metrics from unlabeled stereo images, given coarse information about the scenes and the optical system. Our method alternatively optimizes the metric with a standard stochastic gradient descent, and applies stereo constraints to regularize i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00979","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":"1612.00979","created_at":"2026-05-18T00:55:53.664038+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.00979v1","created_at":"2026-05-18T00:55:53.664038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00979","created_at":"2026-05-18T00:55:53.664038+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPV73BSGZWRC","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPV73BSGZWRCR3EA","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPV73BSG","created_at":"2026-05-18T12:30:41.710351+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/QPV73BSGZWRCR3EAPLSH3X7P3E","json":"https://pith.science/pith/QPV73BSGZWRCR3EAPLSH3X7P3E.json","graph_json":"https://pith.science/api/pith-number/QPV73BSGZWRCR3EAPLSH3X7P3E/graph.json","events_json":"https://pith.science/api/pith-number/QPV73BSGZWRCR3EAPLSH3X7P3E/events.json","paper":"https://pith.science/paper/QPV73BSG"},"agent_actions":{"view_html":"https://pith.science/pith/QPV73BSGZWRCR3EAPLSH3X7P3E","download_json":"https://pith.science/pith/QPV73BSGZWRCR3EAPLSH3X7P3E.json","view_paper":"https://pith.science/paper/QPV73BSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.00979&json=true","fetch_graph":"https://pith.science/api/pith-number/QPV73BSGZWRCR3EAPLSH3X7P3E/graph.json","fetch_events":"https://pith.science/api/pith-number/QPV73BSGZWRCR3EAPLSH3X7P3E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPV73BSGZWRCR3EAPLSH3X7P3E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPV73BSGZWRCR3EAPLSH3X7P3E/action/storage_attestation","attest_author":"https://pith.science/pith/QPV73BSGZWRCR3EAPLSH3X7P3E/action/author_attestation","sign_citation":"https://pith.science/pith/QPV73BSGZWRCR3EAPLSH3X7P3E/action/citation_signature","submit_replication":"https://pith.science/pith/QPV73BSGZWRCR3EAPLSH3X7P3E/action/replication_record"}},"created_at":"2026-05-18T00:55:53.664038+00:00","updated_at":"2026-05-18T00:55:53.664038+00:00"}