{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4363D6Z62ZH4OYAPK5XRDC5RG7","short_pith_number":"pith:4363D6Z6","schema_version":"1.0","canonical_sha256":"e6fdb1fb3ed64fc7600f576f118bb137fc7cc5e59b3d8a048505903040554394","source":{"kind":"arxiv","id":"2312.01897","version":2},"attestation_state":"computed","paper":{"title":"Adapting Short-Term Transformers for Action Detection in Untrimmed Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huan Gao, Limin Wang, Min Yang, Ping Guo","submitted_at":"2023-12-04T13:51:16Z","abstract_excerpt":"Vision Transformer (ViT) has shown high potential in video recognition, owing to its flexible design, adaptable self-attention mechanisms, and the efficacy of masked pre-training. Yet, it remains unclear how to adapt these pre-trained short-term ViTs for temporal action detection (TAD) in untrimmed videos. The existing works treat them as off-the-shelf feature extractors for each short-trimmed snippet without capturing the fine-grained relation among different snippets in a broader temporal context. To mitigate this issue, this paper focuses on designing a new mechanism for adapting these pre-"},"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":"2312.01897","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T13:51:16Z","cross_cats_sorted":[],"title_canon_sha256":"0e4970d29d864b65c2d8adc2dbfebb3b5b2df20fb2388221475ad364d28c1d43","abstract_canon_sha256":"fb6b307e1db10051b8a0940c2a6b067f9c18a10738126b3e8e945d6880939af9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:00.182095Z","signature_b64":"MViqp13cGRktOtJ66x3jpu+ZhuBkquqcuxVM+0XgMVSs+tkuV5tiPeZbe2t+cCSn+aLF5/RkiT8Co46mFlJoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6fdb1fb3ed64fc7600f576f118bb137fc7cc5e59b3d8a048505903040554394","last_reissued_at":"2026-07-05T08:08:00.181680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:00.181680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting Short-Term Transformers for Action Detection in Untrimmed Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huan Gao, Limin Wang, Min Yang, Ping Guo","submitted_at":"2023-12-04T13:51:16Z","abstract_excerpt":"Vision Transformer (ViT) has shown high potential in video recognition, owing to its flexible design, adaptable self-attention mechanisms, and the efficacy of masked pre-training. Yet, it remains unclear how to adapt these pre-trained short-term ViTs for temporal action detection (TAD) in untrimmed videos. The existing works treat them as off-the-shelf feature extractors for each short-trimmed snippet without capturing the fine-grained relation among different snippets in a broader temporal context. To mitigate this issue, this paper focuses on designing a new mechanism for adapting these pre-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01897","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/2312.01897/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":"2312.01897","created_at":"2026-07-05T08:08:00.181742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.01897v2","created_at":"2026-07-05T08:08:00.181742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01897","created_at":"2026-07-05T08:08:00.181742+00:00"},{"alias_kind":"pith_short_12","alias_value":"4363D6Z62ZH4","created_at":"2026-07-05T08:08:00.181742+00:00"},{"alias_kind":"pith_short_16","alias_value":"4363D6Z62ZH4OYAP","created_at":"2026-07-05T08:08:00.181742+00:00"},{"alias_kind":"pith_short_8","alias_value":"4363D6Z6","created_at":"2026-07-05T08:08:00.181742+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06411","citing_title":"Hierarchical Multi-Stage Transformer Architecture for Context-Aware Temporal Action Localization","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4363D6Z62ZH4OYAPK5XRDC5RG7","json":"https://pith.science/pith/4363D6Z62ZH4OYAPK5XRDC5RG7.json","graph_json":"https://pith.science/api/pith-number/4363D6Z62ZH4OYAPK5XRDC5RG7/graph.json","events_json":"https://pith.science/api/pith-number/4363D6Z62ZH4OYAPK5XRDC5RG7/events.json","paper":"https://pith.science/paper/4363D6Z6"},"agent_actions":{"view_html":"https://pith.science/pith/4363D6Z62ZH4OYAPK5XRDC5RG7","download_json":"https://pith.science/pith/4363D6Z62ZH4OYAPK5XRDC5RG7.json","view_paper":"https://pith.science/paper/4363D6Z6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.01897&json=true","fetch_graph":"https://pith.science/api/pith-number/4363D6Z62ZH4OYAPK5XRDC5RG7/graph.json","fetch_events":"https://pith.science/api/pith-number/4363D6Z62ZH4OYAPK5XRDC5RG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4363D6Z62ZH4OYAPK5XRDC5RG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4363D6Z62ZH4OYAPK5XRDC5RG7/action/storage_attestation","attest_author":"https://pith.science/pith/4363D6Z62ZH4OYAPK5XRDC5RG7/action/author_attestation","sign_citation":"https://pith.science/pith/4363D6Z62ZH4OYAPK5XRDC5RG7/action/citation_signature","submit_replication":"https://pith.science/pith/4363D6Z62ZH4OYAPK5XRDC5RG7/action/replication_record"}},"created_at":"2026-07-05T08:08:00.181742+00:00","updated_at":"2026-07-05T08:08:00.181742+00:00"}