{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XHDCMNEKV47Y5QSZVTPCB46LTA","short_pith_number":"pith:XHDCMNEK","schema_version":"1.0","canonical_sha256":"b9c626348aaf3f8ec259acde20f3cb9800add5d6bc8d25ef68bb72fcd1128d64","source":{"kind":"arxiv","id":"1903.07414","version":3},"attestation_state":"computed","paper":{"title":"A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Tak-Wai Hui, Xiaoou Tang","submitted_at":"2019-03-15T04:20:58Z","abstract_excerpt":"Over four decades, the majority addresses the problem of optical flow estimation using variational methods. With the advance of machine learning, some recent works have attempted to address the problem using convolutional neural network (CNN) and have showed promising results. FlowNet2, the state-of-the-art CNN, requires over 160M parameters to achieve accurate flow estimation. Our LiteFlowNet2 outperforms FlowNet2 on Sintel and KITTI benchmarks, while being 25.3 times smaller in the model size and 3.1 times faster in the running speed. LiteFlowNet2 is built on the foundation laid by conventio"},"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":"1903.07414","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-03-15T04:20:58Z","cross_cats_sorted":[],"title_canon_sha256":"8801e8d1f69b1f5c8e94dddd343b4d3088ddf23ba81c42d6d8a7521468f2bf15","abstract_canon_sha256":"b1db9941b4160eb9609e572e279f677b9de1b71b7bfda695493d6d22b56c1a0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:47:56.449245Z","signature_b64":"JO3dTb1XSSilbTlHY879mBfyF0iaHxieiyTyROZL3+A0rAszITQkTgtWtNN1QEnbvjf9zp7Kt5p6nFc2qYonBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9c626348aaf3f8ec259acde20f3cb9800add5d6bc8d25ef68bb72fcd1128d64","last_reissued_at":"2026-07-05T00:47:56.448849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:47:56.448849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Tak-Wai Hui, Xiaoou Tang","submitted_at":"2019-03-15T04:20:58Z","abstract_excerpt":"Over four decades, the majority addresses the problem of optical flow estimation using variational methods. With the advance of machine learning, some recent works have attempted to address the problem using convolutional neural network (CNN) and have showed promising results. FlowNet2, the state-of-the-art CNN, requires over 160M parameters to achieve accurate flow estimation. Our LiteFlowNet2 outperforms FlowNet2 on Sintel and KITTI benchmarks, while being 25.3 times smaller in the model size and 3.1 times faster in the running speed. LiteFlowNet2 is built on the foundation laid by conventio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07414","kind":"arxiv","version":3},"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/1903.07414/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":"1903.07414","created_at":"2026-07-05T00:47:56.448914+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.07414v3","created_at":"2026-07-05T00:47:56.448914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07414","created_at":"2026-07-05T00:47:56.448914+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHDCMNEKV47Y","created_at":"2026-07-05T00:47:56.448914+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHDCMNEKV47Y5QSZ","created_at":"2026-07-05T00:47:56.448914+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHDCMNEK","created_at":"2026-07-05T00:47:56.448914+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03290","citing_title":"Learning Optical Flow Field via Neural Ordinary Differential Equation","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHDCMNEKV47Y5QSZVTPCB46LTA","json":"https://pith.science/pith/XHDCMNEKV47Y5QSZVTPCB46LTA.json","graph_json":"https://pith.science/api/pith-number/XHDCMNEKV47Y5QSZVTPCB46LTA/graph.json","events_json":"https://pith.science/api/pith-number/XHDCMNEKV47Y5QSZVTPCB46LTA/events.json","paper":"https://pith.science/paper/XHDCMNEK"},"agent_actions":{"view_html":"https://pith.science/pith/XHDCMNEKV47Y5QSZVTPCB46LTA","download_json":"https://pith.science/pith/XHDCMNEKV47Y5QSZVTPCB46LTA.json","view_paper":"https://pith.science/paper/XHDCMNEK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.07414&json=true","fetch_graph":"https://pith.science/api/pith-number/XHDCMNEKV47Y5QSZVTPCB46LTA/graph.json","fetch_events":"https://pith.science/api/pith-number/XHDCMNEKV47Y5QSZVTPCB46LTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHDCMNEKV47Y5QSZVTPCB46LTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHDCMNEKV47Y5QSZVTPCB46LTA/action/storage_attestation","attest_author":"https://pith.science/pith/XHDCMNEKV47Y5QSZVTPCB46LTA/action/author_attestation","sign_citation":"https://pith.science/pith/XHDCMNEKV47Y5QSZVTPCB46LTA/action/citation_signature","submit_replication":"https://pith.science/pith/XHDCMNEKV47Y5QSZVTPCB46LTA/action/replication_record"}},"created_at":"2026-07-05T00:47:56.448914+00:00","updated_at":"2026-07-05T00:47:56.448914+00:00"}