{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:K5ZGWLMPIGMKFNB5MWJLHNZEIW","short_pith_number":"pith:K5ZGWLMP","schema_version":"1.0","canonical_sha256":"57726b2d8f4198a2b43d6592b3b72445af30d73dcc3bf2752a1116a32a21fad8","source":{"kind":"arxiv","id":"2108.02183","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dian Li, Huabin Liu, John See, Rui Qian, Shuangrui Ding, Weiyao Lin, Xian Liu, Yuxi Li","submitted_at":"2021-08-04T17:16:18Z","abstract_excerpt":"The crux of self-supervised video representation learning is to build general features from unlabeled videos. However, most recent works have mainly focused on high-level semantics and neglected lower-level representations and their temporal relationship which are crucial for general video understanding. To address these challenges, this paper proposes a multi-level feature optimization framework to improve the generalization and temporal modeling ability of learned video representations. Concretely, high-level features obtained from naive and prototypical contrastive learning are utilized to "},"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":"2108.02183","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-04T17:16:18Z","cross_cats_sorted":[],"title_canon_sha256":"c944a0d3c682857ba7bb43c9321f31eb93853333a0a4c0692fff3289cdd9030e","abstract_canon_sha256":"705470b591caa238b4b6b797078c516e799eac59a47d49c1801da4243b1465a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:34.802541Z","signature_b64":"lzBQV5Ltfd6CoGwzs1HxF+2dAxJnbr0EFU053mLMDvdPSYHLlRZncwgVttxjs7YByUNjrDVC+noOo5htTa3hCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57726b2d8f4198a2b43d6592b3b72445af30d73dcc3bf2752a1116a32a21fad8","last_reissued_at":"2026-07-05T03:06:34.802138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:34.802138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dian Li, Huabin Liu, John See, Rui Qian, Shuangrui Ding, Weiyao Lin, Xian Liu, Yuxi Li","submitted_at":"2021-08-04T17:16:18Z","abstract_excerpt":"The crux of self-supervised video representation learning is to build general features from unlabeled videos. However, most recent works have mainly focused on high-level semantics and neglected lower-level representations and their temporal relationship which are crucial for general video understanding. To address these challenges, this paper proposes a multi-level feature optimization framework to improve the generalization and temporal modeling ability of learned video representations. Concretely, high-level features obtained from naive and prototypical contrastive learning are utilized to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02183","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/2108.02183/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":"2108.02183","created_at":"2026-07-05T03:06:34.802199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.02183v2","created_at":"2026-07-05T03:06:34.802199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02183","created_at":"2026-07-05T03:06:34.802199+00:00"},{"alias_kind":"pith_short_12","alias_value":"K5ZGWLMPIGMK","created_at":"2026-07-05T03:06:34.802199+00:00"},{"alias_kind":"pith_short_16","alias_value":"K5ZGWLMPIGMKFNB5","created_at":"2026-07-05T03:06:34.802199+00:00"},{"alias_kind":"pith_short_8","alias_value":"K5ZGWLMP","created_at":"2026-07-05T03:06:34.802199+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/K5ZGWLMPIGMKFNB5MWJLHNZEIW","json":"https://pith.science/pith/K5ZGWLMPIGMKFNB5MWJLHNZEIW.json","graph_json":"https://pith.science/api/pith-number/K5ZGWLMPIGMKFNB5MWJLHNZEIW/graph.json","events_json":"https://pith.science/api/pith-number/K5ZGWLMPIGMKFNB5MWJLHNZEIW/events.json","paper":"https://pith.science/paper/K5ZGWLMP"},"agent_actions":{"view_html":"https://pith.science/pith/K5ZGWLMPIGMKFNB5MWJLHNZEIW","download_json":"https://pith.science/pith/K5ZGWLMPIGMKFNB5MWJLHNZEIW.json","view_paper":"https://pith.science/paper/K5ZGWLMP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.02183&json=true","fetch_graph":"https://pith.science/api/pith-number/K5ZGWLMPIGMKFNB5MWJLHNZEIW/graph.json","fetch_events":"https://pith.science/api/pith-number/K5ZGWLMPIGMKFNB5MWJLHNZEIW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K5ZGWLMPIGMKFNB5MWJLHNZEIW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K5ZGWLMPIGMKFNB5MWJLHNZEIW/action/storage_attestation","attest_author":"https://pith.science/pith/K5ZGWLMPIGMKFNB5MWJLHNZEIW/action/author_attestation","sign_citation":"https://pith.science/pith/K5ZGWLMPIGMKFNB5MWJLHNZEIW/action/citation_signature","submit_replication":"https://pith.science/pith/K5ZGWLMPIGMKFNB5MWJLHNZEIW/action/replication_record"}},"created_at":"2026-07-05T03:06:34.802199+00:00","updated_at":"2026-07-05T03:06:34.802199+00:00"}