{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QG3BO2JJKFGNNP3HOEWMLEPYQQ","short_pith_number":"pith:QG3BO2JJ","schema_version":"1.0","canonical_sha256":"81b6176929514cd6bf67712cc591f8843d5f2b006c12ca6f795f43f594ea88ec","source":{"kind":"arxiv","id":"2311.15769","version":1},"attestation_state":"computed","paper":{"title":"Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huanjin Yao, Wenhao Wu, Zhiheng Li","submitted_at":"2023-11-27T12:39:42Z","abstract_excerpt":"Large pre-trained vision models achieve impressive success in computer vision. However, fully fine-tuning large models for downstream tasks, particularly in video understanding, can be prohibitively computationally expensive. Recent studies turn their focus towards efficient image-to-video transfer learning. Nevertheless, existing efficient fine-tuning methods lack attention to training memory usage and exploration of transferring a larger model to the video domain. In this paper, we present a novel Spatial-Temporal Side Network for memory-efficient fine-tuning large image models to video unde"},"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":"2311.15769","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T12:39:42Z","cross_cats_sorted":[],"title_canon_sha256":"5280f8b5c86db9a47423df759a73f15a76de2ca9cb498d39dde0a9ed330f5e89","abstract_canon_sha256":"28c39751c53ed49b0c79292a38d0220e0f5fa3de3e50d6ee54ec065ade2359f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:09.147835Z","signature_b64":"QEM0K11wnTt7jemyStFUJJqLUCOoFFXgM/XSiDnvQXTkxGqj/gT1JFo7J6QxDV8i84pIdcGWm+ufFcdTIIasAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81b6176929514cd6bf67712cc591f8843d5f2b006c12ca6f795f43f594ea88ec","last_reissued_at":"2026-07-05T07:17:09.147433Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:09.147433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huanjin Yao, Wenhao Wu, Zhiheng Li","submitted_at":"2023-11-27T12:39:42Z","abstract_excerpt":"Large pre-trained vision models achieve impressive success in computer vision. However, fully fine-tuning large models for downstream tasks, particularly in video understanding, can be prohibitively computationally expensive. Recent studies turn their focus towards efficient image-to-video transfer learning. Nevertheless, existing efficient fine-tuning methods lack attention to training memory usage and exploration of transferring a larger model to the video domain. In this paper, we present a novel Spatial-Temporal Side Network for memory-efficient fine-tuning large image models to video unde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15769","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/2311.15769/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":"2311.15769","created_at":"2026-07-05T07:17:09.147489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15769v1","created_at":"2026-07-05T07:17:09.147489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15769","created_at":"2026-07-05T07:17:09.147489+00:00"},{"alias_kind":"pith_short_12","alias_value":"QG3BO2JJKFGN","created_at":"2026-07-05T07:17:09.147489+00:00"},{"alias_kind":"pith_short_16","alias_value":"QG3BO2JJKFGNNP3H","created_at":"2026-07-05T07:17:09.147489+00:00"},{"alias_kind":"pith_short_8","alias_value":"QG3BO2JJ","created_at":"2026-07-05T07:17:09.147489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26461","citing_title":"$\\text{PKS}^4$:Parallel Kinematic Selective State Space Scanners for Efficient Video Understanding","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20760","citing_title":"Exploring High-Order Self-Similarity for Video Understanding","ref_index":93,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QG3BO2JJKFGNNP3HOEWMLEPYQQ","json":"https://pith.science/pith/QG3BO2JJKFGNNP3HOEWMLEPYQQ.json","graph_json":"https://pith.science/api/pith-number/QG3BO2JJKFGNNP3HOEWMLEPYQQ/graph.json","events_json":"https://pith.science/api/pith-number/QG3BO2JJKFGNNP3HOEWMLEPYQQ/events.json","paper":"https://pith.science/paper/QG3BO2JJ"},"agent_actions":{"view_html":"https://pith.science/pith/QG3BO2JJKFGNNP3HOEWMLEPYQQ","download_json":"https://pith.science/pith/QG3BO2JJKFGNNP3HOEWMLEPYQQ.json","view_paper":"https://pith.science/paper/QG3BO2JJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15769&json=true","fetch_graph":"https://pith.science/api/pith-number/QG3BO2JJKFGNNP3HOEWMLEPYQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QG3BO2JJKFGNNP3HOEWMLEPYQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QG3BO2JJKFGNNP3HOEWMLEPYQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QG3BO2JJKFGNNP3HOEWMLEPYQQ/action/storage_attestation","attest_author":"https://pith.science/pith/QG3BO2JJKFGNNP3HOEWMLEPYQQ/action/author_attestation","sign_citation":"https://pith.science/pith/QG3BO2JJKFGNNP3HOEWMLEPYQQ/action/citation_signature","submit_replication":"https://pith.science/pith/QG3BO2JJKFGNNP3HOEWMLEPYQQ/action/replication_record"}},"created_at":"2026-07-05T07:17:09.147489+00:00","updated_at":"2026-07-05T07:17:09.147489+00:00"}