{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:44RBKAZF5S32X5IV74R5LILEGS","short_pith_number":"pith:44RBKAZF","schema_version":"1.0","canonical_sha256":"e722150325ecb7abf515ff23d5a1643490baf5871b38dcdfab21818fcfbbd3f9","source":{"kind":"arxiv","id":"2008.13426","version":2},"attestation_state":"computed","paper":{"title":"Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianbo Jiao, Jiangliu Wang, Linchao Bao, Shengfeng He, Wei Liu, Yun-hui Liu","submitted_at":"2020-08-31T08:31:56Z","abstract_excerpt":"This paper proposes a novel pretext task to address the self-supervised video representation learning problem. Specifically, given an unlabeled video clip, we compute a series of spatio-temporal statistical summaries, such as the spatial location and dominant direction of the largest motion, the spatial location and dominant color of the largest color diversity along the temporal axis, etc. Then a neural network is built and trained to yield the statistical summaries given the video frames as inputs. In order to alleviate the learning difficulty, we employ several spatial partitioning patterns"},"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":"2008.13426","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-31T08:31:56Z","cross_cats_sorted":[],"title_canon_sha256":"1c8844307d04f72062aa9fa8340297aa45db802552602b3ea1f2c8317259e7f8","abstract_canon_sha256":"ab879c57e3c1ebd3a51bf79233f6983f1c7af39fbf880bf0d374db652a8b5f3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:10:39.880617Z","signature_b64":"ZjXdV4TKygEmrohDgLKKzoNzKasycW+6GtO0Hl+otjLXPzOeWmBnBEpNq1tVeZjve+WohbL8MiJb7fRygTy9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e722150325ecb7abf515ff23d5a1643490baf5871b38dcdfab21818fcfbbd3f9","last_reissued_at":"2026-07-05T02:10:39.880194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:10:39.880194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianbo Jiao, Jiangliu Wang, Linchao Bao, Shengfeng He, Wei Liu, Yun-hui Liu","submitted_at":"2020-08-31T08:31:56Z","abstract_excerpt":"This paper proposes a novel pretext task to address the self-supervised video representation learning problem. Specifically, given an unlabeled video clip, we compute a series of spatio-temporal statistical summaries, such as the spatial location and dominant direction of the largest motion, the spatial location and dominant color of the largest color diversity along the temporal axis, etc. Then a neural network is built and trained to yield the statistical summaries given the video frames as inputs. In order to alleviate the learning difficulty, we employ several spatial partitioning patterns"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.13426","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/2008.13426/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":"2008.13426","created_at":"2026-07-05T02:10:39.880260+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.13426v2","created_at":"2026-07-05T02:10:39.880260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.13426","created_at":"2026-07-05T02:10:39.880260+00:00"},{"alias_kind":"pith_short_12","alias_value":"44RBKAZF5S32","created_at":"2026-07-05T02:10:39.880260+00:00"},{"alias_kind":"pith_short_16","alias_value":"44RBKAZF5S32X5IV","created_at":"2026-07-05T02:10:39.880260+00:00"},{"alias_kind":"pith_short_8","alias_value":"44RBKAZF","created_at":"2026-07-05T02:10:39.880260+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/44RBKAZF5S32X5IV74R5LILEGS","json":"https://pith.science/pith/44RBKAZF5S32X5IV74R5LILEGS.json","graph_json":"https://pith.science/api/pith-number/44RBKAZF5S32X5IV74R5LILEGS/graph.json","events_json":"https://pith.science/api/pith-number/44RBKAZF5S32X5IV74R5LILEGS/events.json","paper":"https://pith.science/paper/44RBKAZF"},"agent_actions":{"view_html":"https://pith.science/pith/44RBKAZF5S32X5IV74R5LILEGS","download_json":"https://pith.science/pith/44RBKAZF5S32X5IV74R5LILEGS.json","view_paper":"https://pith.science/paper/44RBKAZF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.13426&json=true","fetch_graph":"https://pith.science/api/pith-number/44RBKAZF5S32X5IV74R5LILEGS/graph.json","fetch_events":"https://pith.science/api/pith-number/44RBKAZF5S32X5IV74R5LILEGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/44RBKAZF5S32X5IV74R5LILEGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/44RBKAZF5S32X5IV74R5LILEGS/action/storage_attestation","attest_author":"https://pith.science/pith/44RBKAZF5S32X5IV74R5LILEGS/action/author_attestation","sign_citation":"https://pith.science/pith/44RBKAZF5S32X5IV74R5LILEGS/action/citation_signature","submit_replication":"https://pith.science/pith/44RBKAZF5S32X5IV74R5LILEGS/action/replication_record"}},"created_at":"2026-07-05T02:10:39.880260+00:00","updated_at":"2026-07-05T02:10:39.880260+00:00"}