{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FYSEA5ZA2HGYZARREDEQ5SVERW","short_pith_number":"pith:FYSEA5ZA","schema_version":"1.0","canonical_sha256":"2e24407720d1cd8c823120c90ecaa48d9a151d81a10b195dd37e306577088599","source":{"kind":"arxiv","id":"1904.01693","version":1},"attestation_state":"computed","paper":{"title":"Multigrid Predictive Filter Flow for Unsupervised Learning on Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Charless Fowlkes, Shu Kong","submitted_at":"2019-04-02T22:41:48Z","abstract_excerpt":"We introduce multigrid Predictive Filter Flow (mgPFF), a framework for unsupervised learning on videos. The mgPFF takes as input a pair of frames and outputs per-pixel filters to warp one frame to the other. Compared to optical flow used for warping frames, mgPFF is more powerful in modeling sub-pixel movement and dealing with corruption (e.g., motion blur). We develop a multigrid coarse-to-fine modeling strategy that avoids the requirement of learning large filters to capture large displacement. This allows us to train an extremely compact model (4.6MB) which operates in a progressive way ove"},"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":"1904.01693","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-04-02T22:41:48Z","cross_cats_sorted":[],"title_canon_sha256":"820211164a6673a5be33eecabc51f573231a66adcda567f157d2e7c3085a94a1","abstract_canon_sha256":"f5c0afc5140e4910f31361be12d64000cd09e9b10fad33ba90daa00590b01db2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:30.145441Z","signature_b64":"UiXdUVo/ruep2vFgUIYCXvyp3cY/mbgRwckl2+ae5qEjmbA7Vs4bN1BzaDHVrAE7q0B++X4E0AnfvPZQPCu9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e24407720d1cd8c823120c90ecaa48d9a151d81a10b195dd37e306577088599","last_reissued_at":"2026-05-17T23:49:30.144796Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:30.144796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multigrid Predictive Filter Flow for Unsupervised Learning on Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Charless Fowlkes, Shu Kong","submitted_at":"2019-04-02T22:41:48Z","abstract_excerpt":"We introduce multigrid Predictive Filter Flow (mgPFF), a framework for unsupervised learning on videos. The mgPFF takes as input a pair of frames and outputs per-pixel filters to warp one frame to the other. Compared to optical flow used for warping frames, mgPFF is more powerful in modeling sub-pixel movement and dealing with corruption (e.g., motion blur). We develop a multigrid coarse-to-fine modeling strategy that avoids the requirement of learning large filters to capture large displacement. This allows us to train an extremely compact model (4.6MB) which operates in a progressive way ove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01693","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":"1904.01693","created_at":"2026-05-17T23:49:30.144892+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.01693v1","created_at":"2026-05-17T23:49:30.144892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01693","created_at":"2026-05-17T23:49:30.144892+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYSEA5ZA2HGY","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYSEA5ZA2HGYZARR","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYSEA5ZA","created_at":"2026-05-18T12:33:18.533446+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/FYSEA5ZA2HGYZARREDEQ5SVERW","json":"https://pith.science/pith/FYSEA5ZA2HGYZARREDEQ5SVERW.json","graph_json":"https://pith.science/api/pith-number/FYSEA5ZA2HGYZARREDEQ5SVERW/graph.json","events_json":"https://pith.science/api/pith-number/FYSEA5ZA2HGYZARREDEQ5SVERW/events.json","paper":"https://pith.science/paper/FYSEA5ZA"},"agent_actions":{"view_html":"https://pith.science/pith/FYSEA5ZA2HGYZARREDEQ5SVERW","download_json":"https://pith.science/pith/FYSEA5ZA2HGYZARREDEQ5SVERW.json","view_paper":"https://pith.science/paper/FYSEA5ZA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.01693&json=true","fetch_graph":"https://pith.science/api/pith-number/FYSEA5ZA2HGYZARREDEQ5SVERW/graph.json","fetch_events":"https://pith.science/api/pith-number/FYSEA5ZA2HGYZARREDEQ5SVERW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYSEA5ZA2HGYZARREDEQ5SVERW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYSEA5ZA2HGYZARREDEQ5SVERW/action/storage_attestation","attest_author":"https://pith.science/pith/FYSEA5ZA2HGYZARREDEQ5SVERW/action/author_attestation","sign_citation":"https://pith.science/pith/FYSEA5ZA2HGYZARREDEQ5SVERW/action/citation_signature","submit_replication":"https://pith.science/pith/FYSEA5ZA2HGYZARREDEQ5SVERW/action/replication_record"}},"created_at":"2026-05-17T23:49:30.144892+00:00","updated_at":"2026-05-17T23:49:30.144892+00:00"}