{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7WMP4VNVBB3AJ5OAUB3ALDQWEN","short_pith_number":"pith:7WMP4VNV","schema_version":"1.0","canonical_sha256":"fd98fe55b5087604f5c0a076058e162379be90e3fefa9952cb16a5e566aedb6d","source":{"kind":"arxiv","id":"2003.13045","version":2},"attestation_state":"computed","paper":{"title":"Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjie Wang, Donghao Luo, Feiyue Huang, Jiangning Zhang, Jilin Li, Liang Liu, Ruifei He, Yabiao Wang, Ying Tai, Yong Liu","submitted_at":"2020-03-29T14:55:24Z","abstract_excerpt":"Unsupervised learning of optical flow, which leverages the supervision from view synthesis, has emerged as a promising alternative to supervised methods. However, the objective of unsupervised learning is likely to be unreliable in challenging scenes. In this work, we present a framework to use more reliable supervision from transformations. It simply twists the general unsupervised learning pipeline by running another forward pass with transformed data from augmentation, along with using transformed predictions of original data as the self-supervision signal. Besides, we further introduce a l"},"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":"2003.13045","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-29T14:55:24Z","cross_cats_sorted":[],"title_canon_sha256":"5a4a36fb778c7b1f5759fae4395efda2f453da2dffd86f178d71badcfaf11870","abstract_canon_sha256":"7bd888aa9a61bcf6d27abd4100f330db1842a77c37f18964aa4737bbeef6a16c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:55:09.054872Z","signature_b64":"v6EMAz+YaecBhL90vI8T5qK+PPzdgpLFKKKGz8Jpa7MkI4rzAITGjwT+0DcZMzFM7TTAAxEfWPiaF1JGbdPxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd98fe55b5087604f5c0a076058e162379be90e3fefa9952cb16a5e566aedb6d","last_reissued_at":"2026-07-05T01:55:09.054426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:55:09.054426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjie Wang, Donghao Luo, Feiyue Huang, Jiangning Zhang, Jilin Li, Liang Liu, Ruifei He, Yabiao Wang, Ying Tai, Yong Liu","submitted_at":"2020-03-29T14:55:24Z","abstract_excerpt":"Unsupervised learning of optical flow, which leverages the supervision from view synthesis, has emerged as a promising alternative to supervised methods. However, the objective of unsupervised learning is likely to be unreliable in challenging scenes. In this work, we present a framework to use more reliable supervision from transformations. It simply twists the general unsupervised learning pipeline by running another forward pass with transformed data from augmentation, along with using transformed predictions of original data as the self-supervision signal. Besides, we further introduce a l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13045","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2003.13045/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2003.13045","created_at":"2026-07-05T01:55:09.054483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.13045v2","created_at":"2026-07-05T01:55:09.054483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13045","created_at":"2026-07-05T01:55:09.054483+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WMP4VNVBB3A","created_at":"2026-07-05T01:55:09.054483+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WMP4VNVBB3AJ5OA","created_at":"2026-07-05T01:55:09.054483+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WMP4VNV","created_at":"2026-07-05T01:55:09.054483+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/7WMP4VNVBB3AJ5OAUB3ALDQWEN","json":"https://pith.science/pith/7WMP4VNVBB3AJ5OAUB3ALDQWEN.json","graph_json":"https://pith.science/api/pith-number/7WMP4VNVBB3AJ5OAUB3ALDQWEN/graph.json","events_json":"https://pith.science/api/pith-number/7WMP4VNVBB3AJ5OAUB3ALDQWEN/events.json","paper":"https://pith.science/paper/7WMP4VNV"},"agent_actions":{"view_html":"https://pith.science/pith/7WMP4VNVBB3AJ5OAUB3ALDQWEN","download_json":"https://pith.science/pith/7WMP4VNVBB3AJ5OAUB3ALDQWEN.json","view_paper":"https://pith.science/paper/7WMP4VNV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.13045&json=true","fetch_graph":"https://pith.science/api/pith-number/7WMP4VNVBB3AJ5OAUB3ALDQWEN/graph.json","fetch_events":"https://pith.science/api/pith-number/7WMP4VNVBB3AJ5OAUB3ALDQWEN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WMP4VNVBB3AJ5OAUB3ALDQWEN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WMP4VNVBB3AJ5OAUB3ALDQWEN/action/storage_attestation","attest_author":"https://pith.science/pith/7WMP4VNVBB3AJ5OAUB3ALDQWEN/action/author_attestation","sign_citation":"https://pith.science/pith/7WMP4VNVBB3AJ5OAUB3ALDQWEN/action/citation_signature","submit_replication":"https://pith.science/pith/7WMP4VNVBB3AJ5OAUB3ALDQWEN/action/replication_record"}},"created_at":"2026-07-05T01:55:09.054483+00:00","updated_at":"2026-07-05T01:55:09.054483+00:00"}