{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UUEB7UDNSHIYQQ2BK3EFEDXIR7","short_pith_number":"pith:UUEB7UDN","schema_version":"1.0","canonical_sha256":"a5081fd06d91d188434156c8520ee88fd7e46274ebfeeef070d4e9e06f13e02c","source":{"kind":"arxiv","id":"2407.17792","version":2},"attestation_state":"computed","paper":{"title":"Harnessing Temporal Causality for Advanced Temporal Action Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernard Ghanem, Chen-Lin Zhang, Chen Zhao, Fangzhou Mu, Lin Sui, Shuming Liu","submitted_at":"2024-07-25T06:03:02Z","abstract_excerpt":"As a fundamental task in long-form video understanding, temporal action detection (TAD) aims to capture inherent temporal relations in untrimmed videos and identify candidate actions with precise boundaries. Over the years, various networks, including convolutions, graphs, and transformers, have been explored for effective temporal modeling for TAD. However, these modules typically treat past and future information equally, overlooking the crucial fact that changes in action boundaries are essentially causal events. Inspired by this insight, we propose leveraging the temporal causality of acti"},"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":"2407.17792","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-25T06:03:02Z","cross_cats_sorted":[],"title_canon_sha256":"00de339d09e07e7434a644ef062f083070e0f215b186338da62255154784a476","abstract_canon_sha256":"fbc9d549e053c506b7b055ad8bc22f16fb72f327aa91065c5c9ed93d2deb1f93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:46.615879Z","signature_b64":"xPe87guasJA0PC9HDrX2Lijk83QL71P3LWh7GfzShGS+nQ0dMWz+emdfC82BbCl7QfX5LjDWEWmbfJMtAMXEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5081fd06d91d188434156c8520ee88fd7e46274ebfeeef070d4e9e06f13e02c","last_reissued_at":"2026-07-05T08:48:46.615432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:46.615432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing Temporal Causality for Advanced Temporal Action Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernard Ghanem, Chen-Lin Zhang, Chen Zhao, Fangzhou Mu, Lin Sui, Shuming Liu","submitted_at":"2024-07-25T06:03:02Z","abstract_excerpt":"As a fundamental task in long-form video understanding, temporal action detection (TAD) aims to capture inherent temporal relations in untrimmed videos and identify candidate actions with precise boundaries. Over the years, various networks, including convolutions, graphs, and transformers, have been explored for effective temporal modeling for TAD. However, these modules typically treat past and future information equally, overlooking the crucial fact that changes in action boundaries are essentially causal events. Inspired by this insight, we propose leveraging the temporal causality of acti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17792","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/2407.17792/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":"2407.17792","created_at":"2026-07-05T08:48:46.615493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.17792v2","created_at":"2026-07-05T08:48:46.615493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17792","created_at":"2026-07-05T08:48:46.615493+00:00"},{"alias_kind":"pith_short_12","alias_value":"UUEB7UDNSHIY","created_at":"2026-07-05T08:48:46.615493+00:00"},{"alias_kind":"pith_short_16","alias_value":"UUEB7UDNSHIYQQ2B","created_at":"2026-07-05T08:48:46.615493+00:00"},{"alias_kind":"pith_short_8","alias_value":"UUEB7UDN","created_at":"2026-07-05T08:48:46.615493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31127","citing_title":"SkillSpotter: Pose-Aware Multi-View Skilled Action Detection and Grading in Ego-Exo Videos","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24496","citing_title":"EgoAction: Egocentric Action Composition with Reliability-Aware Temporal Fusion for the EPIC-KITCHENS Action Detection Challenge at CVPR 2026","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22695","citing_title":"Improving Viewpoint-Invariance and Temporal Consistency for Action Detection","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06185","citing_title":"Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18274","citing_title":"LiquidTAD: Efficient Temporal Action Detection via Parallel Liquid-Inspired Temporal Relaxation","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UUEB7UDNSHIYQQ2BK3EFEDXIR7","json":"https://pith.science/pith/UUEB7UDNSHIYQQ2BK3EFEDXIR7.json","graph_json":"https://pith.science/api/pith-number/UUEB7UDNSHIYQQ2BK3EFEDXIR7/graph.json","events_json":"https://pith.science/api/pith-number/UUEB7UDNSHIYQQ2BK3EFEDXIR7/events.json","paper":"https://pith.science/paper/UUEB7UDN"},"agent_actions":{"view_html":"https://pith.science/pith/UUEB7UDNSHIYQQ2BK3EFEDXIR7","download_json":"https://pith.science/pith/UUEB7UDNSHIYQQ2BK3EFEDXIR7.json","view_paper":"https://pith.science/paper/UUEB7UDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.17792&json=true","fetch_graph":"https://pith.science/api/pith-number/UUEB7UDNSHIYQQ2BK3EFEDXIR7/graph.json","fetch_events":"https://pith.science/api/pith-number/UUEB7UDNSHIYQQ2BK3EFEDXIR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UUEB7UDNSHIYQQ2BK3EFEDXIR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UUEB7UDNSHIYQQ2BK3EFEDXIR7/action/storage_attestation","attest_author":"https://pith.science/pith/UUEB7UDNSHIYQQ2BK3EFEDXIR7/action/author_attestation","sign_citation":"https://pith.science/pith/UUEB7UDNSHIYQQ2BK3EFEDXIR7/action/citation_signature","submit_replication":"https://pith.science/pith/UUEB7UDNSHIYQQ2BK3EFEDXIR7/action/replication_record"}},"created_at":"2026-07-05T08:48:46.615493+00:00","updated_at":"2026-07-05T08:48:46.615493+00:00"}