{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BNTKO74PZFNPTTROKRJVXPWIQL","short_pith_number":"pith:BNTKO74P","schema_version":"1.0","canonical_sha256":"0b66a77f8fc95af9ce2e54535bbec882c93e3dad254cb75e7ccd122e6f4dedd0","source":{"kind":"arxiv","id":"2001.00294","version":1},"attestation_state":"computed","paper":{"title":"Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Ma, Chang Liu, Dezhao Luo, Dongbao Yang, Qixiang Ye, Weiping Wang, Yu Zhou","submitted_at":"2020-01-02T02:15:24Z","abstract_excerpt":"We propose a novel self-supervised method, referred to as Video Cloze Procedure (VCP), to learn rich spatial-temporal representations. VCP first generates \"blanks\" by withholding video clips and then creates \"options\" by applying spatio-temporal operations on the withheld clips. Finally, it fills the blanks with \"options\" and learns representations by predicting the categories of operations applied on the clips. VCP can act as either a proxy task or a target task in self-supervised learning. As a proxy task, it converts rich self-supervised representations into video clip operations (options),"},"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":"2001.00294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-02T02:15:24Z","cross_cats_sorted":[],"title_canon_sha256":"63da8be4480aa0c79e53e49efa7eb21e69734637d9fa00f387fc1929f9aebc30","abstract_canon_sha256":"fd53c7f82de360b6a9fc0b96b36ca201b4f5a959388349f3b53cb4090be5515e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:29:22.833777Z","signature_b64":"5VM7EftvQ4MAznjCYfkEbPmTC5pw4AqZzjjpVSwp218KnWOQaOIXVoK4iuXRzae/oMvWdq1XIhXa4+zqcuWHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b66a77f8fc95af9ce2e54535bbec882c93e3dad254cb75e7ccd122e6f4dedd0","last_reissued_at":"2026-07-05T00:29:22.833380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:29:22.833380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Ma, Chang Liu, Dezhao Luo, Dongbao Yang, Qixiang Ye, Weiping Wang, Yu Zhou","submitted_at":"2020-01-02T02:15:24Z","abstract_excerpt":"We propose a novel self-supervised method, referred to as Video Cloze Procedure (VCP), to learn rich spatial-temporal representations. VCP first generates \"blanks\" by withholding video clips and then creates \"options\" by applying spatio-temporal operations on the withheld clips. Finally, it fills the blanks with \"options\" and learns representations by predicting the categories of operations applied on the clips. VCP can act as either a proxy task or a target task in self-supervised learning. As a proxy task, it converts rich self-supervised representations into video clip operations (options),"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00294","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2001.00294/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":"2001.00294","created_at":"2026-07-05T00:29:22.833436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.00294v1","created_at":"2026-07-05T00:29:22.833436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00294","created_at":"2026-07-05T00:29:22.833436+00:00"},{"alias_kind":"pith_short_12","alias_value":"BNTKO74PZFNP","created_at":"2026-07-05T00:29:22.833436+00:00"},{"alias_kind":"pith_short_16","alias_value":"BNTKO74PZFNPTTRO","created_at":"2026-07-05T00:29:22.833436+00:00"},{"alias_kind":"pith_short_8","alias_value":"BNTKO74P","created_at":"2026-07-05T00:29:22.833436+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/BNTKO74PZFNPTTROKRJVXPWIQL","json":"https://pith.science/pith/BNTKO74PZFNPTTROKRJVXPWIQL.json","graph_json":"https://pith.science/api/pith-number/BNTKO74PZFNPTTROKRJVXPWIQL/graph.json","events_json":"https://pith.science/api/pith-number/BNTKO74PZFNPTTROKRJVXPWIQL/events.json","paper":"https://pith.science/paper/BNTKO74P"},"agent_actions":{"view_html":"https://pith.science/pith/BNTKO74PZFNPTTROKRJVXPWIQL","download_json":"https://pith.science/pith/BNTKO74PZFNPTTROKRJVXPWIQL.json","view_paper":"https://pith.science/paper/BNTKO74P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.00294&json=true","fetch_graph":"https://pith.science/api/pith-number/BNTKO74PZFNPTTROKRJVXPWIQL/graph.json","fetch_events":"https://pith.science/api/pith-number/BNTKO74PZFNPTTROKRJVXPWIQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BNTKO74PZFNPTTROKRJVXPWIQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BNTKO74PZFNPTTROKRJVXPWIQL/action/storage_attestation","attest_author":"https://pith.science/pith/BNTKO74PZFNPTTROKRJVXPWIQL/action/author_attestation","sign_citation":"https://pith.science/pith/BNTKO74PZFNPTTROKRJVXPWIQL/action/citation_signature","submit_replication":"https://pith.science/pith/BNTKO74PZFNPTTROKRJVXPWIQL/action/replication_record"}},"created_at":"2026-07-05T00:29:22.833436+00:00","updated_at":"2026-07-05T00:29:22.833436+00:00"}