{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OIAMGPL3EEJFVD4YH5JNSUHXEN","short_pith_number":"pith:OIAMGPL3","schema_version":"1.0","canonical_sha256":"7200c33d7b21125a8f983f52d950f723484278a2132855b909692dcd2a945b4e","source":{"kind":"arxiv","id":"1808.07507","version":1},"attestation_state":"computed","paper":{"title":"Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Irfan Essa, Rishi Madhok, Unaiza Ahsan","submitted_at":"2018-08-22T18:18:44Z","abstract_excerpt":"We propose a self-supervised learning method to jointly reason about spatial and temporal context for video recognition. Recent self-supervised approaches have used spatial context [9, 34] as well as temporal coherency [32] but a combination of the two requires extensive preprocessing such as tracking objects through millions of video frames [59] or computing optical flow to determine frame regions with high motion [30]. We propose to combine spatial and temporal context in one self-supervised framework without any heavy preprocessing. We divide multiple video frames into grids of patches 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":"1808.07507","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-22T18:18:44Z","cross_cats_sorted":[],"title_canon_sha256":"299f402402612aad47339403276a4849d2d61882dbf9e757826a7bcbf157b1ed","abstract_canon_sha256":"ebf50464155074c2116dc53b1f670e573f677130df7961b468d5f13c9d2c84a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:27.122693Z","signature_b64":"ocqehiLjUB5yK2+0SkRB7jn0liCfEy2z0wk6MhvpuP6o75lDx3p+bHr0ogdIp0HPfo5xaUyiSPNfOsOWN4y7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7200c33d7b21125a8f983f52d950f723484278a2132855b909692dcd2a945b4e","last_reissued_at":"2026-05-18T00:07:27.122210Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:27.122210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Irfan Essa, Rishi Madhok, Unaiza Ahsan","submitted_at":"2018-08-22T18:18:44Z","abstract_excerpt":"We propose a self-supervised learning method to jointly reason about spatial and temporal context for video recognition. Recent self-supervised approaches have used spatial context [9, 34] as well as temporal coherency [32] but a combination of the two requires extensive preprocessing such as tracking objects through millions of video frames [59] or computing optical flow to determine frame regions with high motion [30]. We propose to combine spatial and temporal context in one self-supervised framework without any heavy preprocessing. We divide multiple video frames into grids of patches and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07507","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":"1808.07507","created_at":"2026-05-18T00:07:27.122282+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.07507v1","created_at":"2026-05-18T00:07:27.122282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07507","created_at":"2026-05-18T00:07:27.122282+00:00"},{"alias_kind":"pith_short_12","alias_value":"OIAMGPL3EEJF","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OIAMGPL3EEJFVD4Y","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OIAMGPL3","created_at":"2026-05-18T12:32:43.782077+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/OIAMGPL3EEJFVD4YH5JNSUHXEN","json":"https://pith.science/pith/OIAMGPL3EEJFVD4YH5JNSUHXEN.json","graph_json":"https://pith.science/api/pith-number/OIAMGPL3EEJFVD4YH5JNSUHXEN/graph.json","events_json":"https://pith.science/api/pith-number/OIAMGPL3EEJFVD4YH5JNSUHXEN/events.json","paper":"https://pith.science/paper/OIAMGPL3"},"agent_actions":{"view_html":"https://pith.science/pith/OIAMGPL3EEJFVD4YH5JNSUHXEN","download_json":"https://pith.science/pith/OIAMGPL3EEJFVD4YH5JNSUHXEN.json","view_paper":"https://pith.science/paper/OIAMGPL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.07507&json=true","fetch_graph":"https://pith.science/api/pith-number/OIAMGPL3EEJFVD4YH5JNSUHXEN/graph.json","fetch_events":"https://pith.science/api/pith-number/OIAMGPL3EEJFVD4YH5JNSUHXEN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OIAMGPL3EEJFVD4YH5JNSUHXEN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OIAMGPL3EEJFVD4YH5JNSUHXEN/action/storage_attestation","attest_author":"https://pith.science/pith/OIAMGPL3EEJFVD4YH5JNSUHXEN/action/author_attestation","sign_citation":"https://pith.science/pith/OIAMGPL3EEJFVD4YH5JNSUHXEN/action/citation_signature","submit_replication":"https://pith.science/pith/OIAMGPL3EEJFVD4YH5JNSUHXEN/action/replication_record"}},"created_at":"2026-05-18T00:07:27.122282+00:00","updated_at":"2026-05-18T00:07:27.122282+00:00"}