{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OVWEGSNT24XLKQ2F77FNDFWQ6E","short_pith_number":"pith:OVWEGSNT","schema_version":"1.0","canonical_sha256":"756c4349b3d72eb54345ffcad196d0f12d65912082d783709031326021bdef9f","source":{"kind":"arxiv","id":"2205.00506","version":1},"attestation_state":"computed","paper":{"title":"Preserve Pre-trained Knowledge: Transfer Learning With Self-Distillation For Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gaoang Wang, Guanhong Wang, Keyu Lu, Yang Zhou, Zhanhao He","submitted_at":"2022-05-01T16:31:25Z","abstract_excerpt":"Video-based action recognition is one of the most popular topics in computer vision. With recent advances of selfsupervised video representation learning approaches, action recognition usually follows a two-stage training framework, i.e., self-supervised pre-training on large-scale unlabeled sets and transfer learning on a downstream labeled set. However, catastrophic forgetting of the pre-trained knowledge becomes the main issue in the downstream transfer learning of action recognition, resulting in a sub-optimal solution. In this paper, to alleviate the above issue, we propose a novel transf"},"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":"2205.00506","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-01T16:31:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dd9846b0e86755754c5dc2e7130e865b24efc94d04401198fd63d8e672952e4c","abstract_canon_sha256":"9a29a0fe1aad91c3402877cd6a1fa7542baae969395f847662679422419abcf1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:13.517976Z","signature_b64":"maWUMHwA+s/jrudpC9f7DlMVQPX4LuzseqGbWjMPj9Hoq3QIzakc/8+TQeCZqHDO2KJSsMFe3O/U8+H4tghPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"756c4349b3d72eb54345ffcad196d0f12d65912082d783709031326021bdef9f","last_reissued_at":"2026-07-05T04:19:13.517492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:13.517492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preserve Pre-trained Knowledge: Transfer Learning With Self-Distillation For Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gaoang Wang, Guanhong Wang, Keyu Lu, Yang Zhou, Zhanhao He","submitted_at":"2022-05-01T16:31:25Z","abstract_excerpt":"Video-based action recognition is one of the most popular topics in computer vision. With recent advances of selfsupervised video representation learning approaches, action recognition usually follows a two-stage training framework, i.e., self-supervised pre-training on large-scale unlabeled sets and transfer learning on a downstream labeled set. However, catastrophic forgetting of the pre-trained knowledge becomes the main issue in the downstream transfer learning of action recognition, resulting in a sub-optimal solution. In this paper, to alleviate the above issue, we propose a novel transf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.00506","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/2205.00506/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":"2205.00506","created_at":"2026-07-05T04:19:13.517558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.00506v1","created_at":"2026-07-05T04:19:13.517558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.00506","created_at":"2026-07-05T04:19:13.517558+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVWEGSNT24XL","created_at":"2026-07-05T04:19:13.517558+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVWEGSNT24XLKQ2F","created_at":"2026-07-05T04:19:13.517558+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVWEGSNT","created_at":"2026-07-05T04:19:13.517558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12426","citing_title":"DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OVWEGSNT24XLKQ2F77FNDFWQ6E","json":"https://pith.science/pith/OVWEGSNT24XLKQ2F77FNDFWQ6E.json","graph_json":"https://pith.science/api/pith-number/OVWEGSNT24XLKQ2F77FNDFWQ6E/graph.json","events_json":"https://pith.science/api/pith-number/OVWEGSNT24XLKQ2F77FNDFWQ6E/events.json","paper":"https://pith.science/paper/OVWEGSNT"},"agent_actions":{"view_html":"https://pith.science/pith/OVWEGSNT24XLKQ2F77FNDFWQ6E","download_json":"https://pith.science/pith/OVWEGSNT24XLKQ2F77FNDFWQ6E.json","view_paper":"https://pith.science/paper/OVWEGSNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.00506&json=true","fetch_graph":"https://pith.science/api/pith-number/OVWEGSNT24XLKQ2F77FNDFWQ6E/graph.json","fetch_events":"https://pith.science/api/pith-number/OVWEGSNT24XLKQ2F77FNDFWQ6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVWEGSNT24XLKQ2F77FNDFWQ6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVWEGSNT24XLKQ2F77FNDFWQ6E/action/storage_attestation","attest_author":"https://pith.science/pith/OVWEGSNT24XLKQ2F77FNDFWQ6E/action/author_attestation","sign_citation":"https://pith.science/pith/OVWEGSNT24XLKQ2F77FNDFWQ6E/action/citation_signature","submit_replication":"https://pith.science/pith/OVWEGSNT24XLKQ2F77FNDFWQ6E/action/replication_record"}},"created_at":"2026-07-05T04:19:13.517558+00:00","updated_at":"2026-07-05T04:19:13.517558+00:00"}