{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CKEGZTX6VG6HOXUVJZB7D7FB7J","short_pith_number":"pith:CKEGZTX6","schema_version":"1.0","canonical_sha256":"12886ccefea9bc775e954e43f1fca1fa7a67aa9de8ca65f59f8369a18b43a62d","source":{"kind":"arxiv","id":"2404.00653","version":1},"attestation_state":"computed","paper":{"title":"Dual DETRs for Multi-Label Temporal Action Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gangshan Wu, Guozhen Zhang, Jing Tan, Limin Wang, Yuhan Zhu","submitted_at":"2024-03-31T11:43:39Z","abstract_excerpt":"Temporal Action Detection (TAD) aims to identify the action boundaries and the corresponding category within untrimmed videos. Inspired by the success of DETR in object detection, several methods have adapted the query-based framework to the TAD task. However, these approaches primarily followed DETR to predict actions at the instance level (i.e., identify each action by its center point), leading to sub-optimal boundary localization. To address this issue, we propose a new Dual-level query-based TAD framework, namely DualDETR, to detect actions from both instance-level and boundary-level. Dec"},"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":"2404.00653","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-31T11:43:39Z","cross_cats_sorted":[],"title_canon_sha256":"e9f10c7499e9ef362cc08857fc881bf44f6645ccb0b41695770aebb5c7fcb36c","abstract_canon_sha256":"ffa2e5425ced7b31c58ac6e587cee03891c8ba43a99e89c06d21ac7a3eb1ef39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:54.881857Z","signature_b64":"7i97x3fROQfEB/YGmqoU5/QmhrPKJeNQ6ikWq7ChfmP0fXXEqCyaTe2bnxg08eDNq04yc4c6BWBjcvolTIRKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12886ccefea9bc775e954e43f1fca1fa7a67aa9de8ca65f59f8369a18b43a62d","last_reissued_at":"2026-07-05T08:02:54.881370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:54.881370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual DETRs for Multi-Label Temporal Action Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gangshan Wu, Guozhen Zhang, Jing Tan, Limin Wang, Yuhan Zhu","submitted_at":"2024-03-31T11:43:39Z","abstract_excerpt":"Temporal Action Detection (TAD) aims to identify the action boundaries and the corresponding category within untrimmed videos. Inspired by the success of DETR in object detection, several methods have adapted the query-based framework to the TAD task. However, these approaches primarily followed DETR to predict actions at the instance level (i.e., identify each action by its center point), leading to sub-optimal boundary localization. To address this issue, we propose a new Dual-level query-based TAD framework, namely DualDETR, to detect actions from both instance-level and boundary-level. Dec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00653","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/2404.00653/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":"2404.00653","created_at":"2026-07-05T08:02:54.881441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00653v1","created_at":"2026-07-05T08:02:54.881441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00653","created_at":"2026-07-05T08:02:54.881441+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKEGZTX6VG6H","created_at":"2026-07-05T08:02:54.881441+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKEGZTX6VG6HOXUV","created_at":"2026-07-05T08:02:54.881441+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKEGZTX6","created_at":"2026-07-05T08:02:54.881441+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/CKEGZTX6VG6HOXUVJZB7D7FB7J","json":"https://pith.science/pith/CKEGZTX6VG6HOXUVJZB7D7FB7J.json","graph_json":"https://pith.science/api/pith-number/CKEGZTX6VG6HOXUVJZB7D7FB7J/graph.json","events_json":"https://pith.science/api/pith-number/CKEGZTX6VG6HOXUVJZB7D7FB7J/events.json","paper":"https://pith.science/paper/CKEGZTX6"},"agent_actions":{"view_html":"https://pith.science/pith/CKEGZTX6VG6HOXUVJZB7D7FB7J","download_json":"https://pith.science/pith/CKEGZTX6VG6HOXUVJZB7D7FB7J.json","view_paper":"https://pith.science/paper/CKEGZTX6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00653&json=true","fetch_graph":"https://pith.science/api/pith-number/CKEGZTX6VG6HOXUVJZB7D7FB7J/graph.json","fetch_events":"https://pith.science/api/pith-number/CKEGZTX6VG6HOXUVJZB7D7FB7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKEGZTX6VG6HOXUVJZB7D7FB7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKEGZTX6VG6HOXUVJZB7D7FB7J/action/storage_attestation","attest_author":"https://pith.science/pith/CKEGZTX6VG6HOXUVJZB7D7FB7J/action/author_attestation","sign_citation":"https://pith.science/pith/CKEGZTX6VG6HOXUVJZB7D7FB7J/action/citation_signature","submit_replication":"https://pith.science/pith/CKEGZTX6VG6HOXUVJZB7D7FB7J/action/replication_record"}},"created_at":"2026-07-05T08:02:54.881441+00:00","updated_at":"2026-07-05T08:02:54.881441+00:00"}