{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RSMOU66B6Z5G3U5JYM36JOIRIJ","short_pith_number":"pith:RSMOU66B","schema_version":"1.0","canonical_sha256":"8c98ea7bc1f67a6dd3a9c337e4b911426a890b3bc9e2eba8f7370fd0eadab9b6","source":{"kind":"arxiv","id":"2312.01431","version":4},"attestation_state":"computed","paper":{"title":"D$^2$ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangming Lu, Jiandong Tian, Jun Yu, Qizhong Tan, Wenjie Pei","submitted_at":"2023-12-03T15:40:10Z","abstract_excerpt":"Adapting pre-trained image models to video modality has proven to be an effective strategy for robust few-shot action recognition. In this work, we explore the potential of adapter tuning in image-to-video model adaptation and propose a novel video adapter tuning framework, called Disentangled-and-Deformable Spatio-Temporal Adapter (D$^2$ST-Adapter). It features a lightweight design, low adaptation overhead and powerful spatio-temporal feature adaptation capabilities. D$^2$ST-Adapter is structured with an internal dual-pathway architecture that enables built-in disentangled encoding of spatial"},"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":"2312.01431","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-03T15:40:10Z","cross_cats_sorted":[],"title_canon_sha256":"b2ee4f8146b2e4bcdf8c2bf1bec6f4dc970afcbc88b10155e84ccf18d3429f83","abstract_canon_sha256":"0c0e8838b697c0bd13d2b99ff9e085e977a53c147f2efb5115209e32fb8a4069"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:57.469214Z","signature_b64":"GclwS0FqyJEDEVmyRFGvARE+dD1Kg1GtFvMCetsEzguah9NQERBlCoMEXBZg2OIP8IGCJLOMOPtiMxUmuAFgCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c98ea7bc1f67a6dd3a9c337e4b911426a890b3bc9e2eba8f7370fd0eadab9b6","last_reissued_at":"2026-07-05T11:28:57.468696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:57.468696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D$^2$ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangming Lu, Jiandong Tian, Jun Yu, Qizhong Tan, Wenjie Pei","submitted_at":"2023-12-03T15:40:10Z","abstract_excerpt":"Adapting pre-trained image models to video modality has proven to be an effective strategy for robust few-shot action recognition. In this work, we explore the potential of adapter tuning in image-to-video model adaptation and propose a novel video adapter tuning framework, called Disentangled-and-Deformable Spatio-Temporal Adapter (D$^2$ST-Adapter). It features a lightweight design, low adaptation overhead and powerful spatio-temporal feature adaptation capabilities. D$^2$ST-Adapter is structured with an internal dual-pathway architecture that enables built-in disentangled encoding of spatial"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01431","kind":"arxiv","version":4},"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/2312.01431/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":"2312.01431","created_at":"2026-07-05T11:28:57.468756+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.01431v4","created_at":"2026-07-05T11:28:57.468756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01431","created_at":"2026-07-05T11:28:57.468756+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSMOU66B6Z5G","created_at":"2026-07-05T11:28:57.468756+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSMOU66B6Z5G3U5J","created_at":"2026-07-05T11:28:57.468756+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSMOU66B","created_at":"2026-07-05T11:28:57.468756+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.11335","citing_title":"Video-to-Task Learning via Motion-Guided Attention for Few-Shot Action Recognition","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RSMOU66B6Z5G3U5JYM36JOIRIJ","json":"https://pith.science/pith/RSMOU66B6Z5G3U5JYM36JOIRIJ.json","graph_json":"https://pith.science/api/pith-number/RSMOU66B6Z5G3U5JYM36JOIRIJ/graph.json","events_json":"https://pith.science/api/pith-number/RSMOU66B6Z5G3U5JYM36JOIRIJ/events.json","paper":"https://pith.science/paper/RSMOU66B"},"agent_actions":{"view_html":"https://pith.science/pith/RSMOU66B6Z5G3U5JYM36JOIRIJ","download_json":"https://pith.science/pith/RSMOU66B6Z5G3U5JYM36JOIRIJ.json","view_paper":"https://pith.science/paper/RSMOU66B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.01431&json=true","fetch_graph":"https://pith.science/api/pith-number/RSMOU66B6Z5G3U5JYM36JOIRIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/RSMOU66B6Z5G3U5JYM36JOIRIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSMOU66B6Z5G3U5JYM36JOIRIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSMOU66B6Z5G3U5JYM36JOIRIJ/action/storage_attestation","attest_author":"https://pith.science/pith/RSMOU66B6Z5G3U5JYM36JOIRIJ/action/author_attestation","sign_citation":"https://pith.science/pith/RSMOU66B6Z5G3U5JYM36JOIRIJ/action/citation_signature","submit_replication":"https://pith.science/pith/RSMOU66B6Z5G3U5JYM36JOIRIJ/action/replication_record"}},"created_at":"2026-07-05T11:28:57.468756+00:00","updated_at":"2026-07-05T11:28:57.468756+00:00"}