{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6FK35NNRJWA5QWIJLL3CWFAACL","short_pith_number":"pith:6FK35NNR","schema_version":"1.0","canonical_sha256":"f155beb5b14d81d859095af62b140012f58da514f482e0dc7a9fd88f108a1226","source":{"kind":"arxiv","id":"2507.06411","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical Multi-Stage Transformer Architecture for Context-Aware Temporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arslan Munir, Hayat Ullah, Oliver Nina","submitted_at":"2025-07-08T21:28:16Z","abstract_excerpt":"Inspired by the recent success of transformers and multi-stage architectures in video recognition and object detection domains. We thoroughly explore the rich spatio-temporal properties of transformers within a multi-stage architecture paradigm for the temporal action localization (TAL) task. This exploration led to the development of a hierarchical multi-stage transformer architecture called PCL-Former, where each subtask is handled by a dedicated transformer module with a specialized loss function. Specifically, the Proposal-Former identifies candidate segments in an untrimmed video that may"},"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":"2507.06411","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T21:28:16Z","cross_cats_sorted":[],"title_canon_sha256":"3dda4f9d17b4ac471fe9c2a3d4871a9e6e522a9f501c767c3ea104f0d84f1ec6","abstract_canon_sha256":"45e8dd85bbe91ad29751111579efd8cb1c3d9d32cd83b7615983265239455df0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:13.271387Z","signature_b64":"o4pw98MfqzxJ3u17ngnHwk7c2lRQdunhDZ81uKBoHOmqhQlJRPFu1j0m/CbrAsMH7LbgbCTwQ2hJ1jOZx+30Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f155beb5b14d81d859095af62b140012f58da514f482e0dc7a9fd88f108a1226","last_reissued_at":"2026-07-05T11:39:13.270916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:13.270916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Multi-Stage Transformer Architecture for Context-Aware Temporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arslan Munir, Hayat Ullah, Oliver Nina","submitted_at":"2025-07-08T21:28:16Z","abstract_excerpt":"Inspired by the recent success of transformers and multi-stage architectures in video recognition and object detection domains. We thoroughly explore the rich spatio-temporal properties of transformers within a multi-stage architecture paradigm for the temporal action localization (TAL) task. This exploration led to the development of a hierarchical multi-stage transformer architecture called PCL-Former, where each subtask is handled by a dedicated transformer module with a specialized loss function. Specifically, the Proposal-Former identifies candidate segments in an untrimmed video that may"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06411","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/2507.06411/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":"2507.06411","created_at":"2026-07-05T11:39:13.270969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06411v2","created_at":"2026-07-05T11:39:13.270969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06411","created_at":"2026-07-05T11:39:13.270969+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FK35NNRJWA5","created_at":"2026-07-05T11:39:13.270969+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FK35NNRJWA5QWIJ","created_at":"2026-07-05T11:39:13.270969+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FK35NNR","created_at":"2026-07-05T11:39:13.270969+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/6FK35NNRJWA5QWIJLL3CWFAACL","json":"https://pith.science/pith/6FK35NNRJWA5QWIJLL3CWFAACL.json","graph_json":"https://pith.science/api/pith-number/6FK35NNRJWA5QWIJLL3CWFAACL/graph.json","events_json":"https://pith.science/api/pith-number/6FK35NNRJWA5QWIJLL3CWFAACL/events.json","paper":"https://pith.science/paper/6FK35NNR"},"agent_actions":{"view_html":"https://pith.science/pith/6FK35NNRJWA5QWIJLL3CWFAACL","download_json":"https://pith.science/pith/6FK35NNRJWA5QWIJLL3CWFAACL.json","view_paper":"https://pith.science/paper/6FK35NNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06411&json=true","fetch_graph":"https://pith.science/api/pith-number/6FK35NNRJWA5QWIJLL3CWFAACL/graph.json","fetch_events":"https://pith.science/api/pith-number/6FK35NNRJWA5QWIJLL3CWFAACL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FK35NNRJWA5QWIJLL3CWFAACL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FK35NNRJWA5QWIJLL3CWFAACL/action/storage_attestation","attest_author":"https://pith.science/pith/6FK35NNRJWA5QWIJLL3CWFAACL/action/author_attestation","sign_citation":"https://pith.science/pith/6FK35NNRJWA5QWIJLL3CWFAACL/action/citation_signature","submit_replication":"https://pith.science/pith/6FK35NNRJWA5QWIJLL3CWFAACL/action/replication_record"}},"created_at":"2026-07-05T11:39:13.270969+00:00","updated_at":"2026-07-05T11:39:13.270969+00:00"}