{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z63ZQWLVNISXAYMDDDX4E73PPC","short_pith_number":"pith:Z63ZQWLV","schema_version":"1.0","canonical_sha256":"cfb79859756a2570618318efc27f6f78ad669f91ac06878ac48dcfc8882cfb94","source":{"kind":"arxiv","id":"2501.11124","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Ke Zhang, Quan Zhang, Rui Yuan, Xi Lin, Xi Tang, Yuxin Qi","submitted_at":"2025-01-19T17:31:40Z","abstract_excerpt":"Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training the fully-supervised detection head. We argue that the noise in pseudo-labels would interfere with the learning of fully-supervised detection head, leading to significant performance leakage. Issues with noisy labels include:(1) inaccurate boundary localization; (2) undetected short action clips; (3) multiple adjacent segments incorrectly detected as one segment. To target the"},"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":"2501.11124","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-19T17:31:40Z","cross_cats_sorted":[],"title_canon_sha256":"73d8ef956078d938d11a4f9b4cf0a546d9ee3e367eca711b7ed43469c88031e1","abstract_canon_sha256":"379a950b4da58dcb35fd6c3266f71d70333e3fa9f06ea049e0ce9de0006fcb68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:13.809734Z","signature_b64":"tY9X1ii2ENt3vtF5so6ONvNmX6uUihyr9q4DjS6DbjvnfyL87DL7RndadI51wzap770GCbZWHpFRMSmSkRN0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfb79859756a2570618318efc27f6f78ad669f91ac06878ac48dcfc8882cfb94","last_reissued_at":"2026-07-05T10:56:13.809283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:13.809283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Ke Zhang, Quan Zhang, Rui Yuan, Xi Lin, Xi Tang, Yuxin Qi","submitted_at":"2025-01-19T17:31:40Z","abstract_excerpt":"Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training the fully-supervised detection head. We argue that the noise in pseudo-labels would interfere with the learning of fully-supervised detection head, leading to significant performance leakage. Issues with noisy labels include:(1) inaccurate boundary localization; (2) undetected short action clips; (3) multiple adjacent segments incorrectly detected as one segment. To target the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11124","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/2501.11124/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":"2501.11124","created_at":"2026-07-05T10:56:13.809334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11124v2","created_at":"2026-07-05T10:56:13.809334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11124","created_at":"2026-07-05T10:56:13.809334+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z63ZQWLVNISX","created_at":"2026-07-05T10:56:13.809334+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z63ZQWLVNISXAYMD","created_at":"2026-07-05T10:56:13.809334+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z63ZQWLV","created_at":"2026-07-05T10:56:13.809334+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03737","citing_title":"ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z63ZQWLVNISXAYMDDDX4E73PPC","json":"https://pith.science/pith/Z63ZQWLVNISXAYMDDDX4E73PPC.json","graph_json":"https://pith.science/api/pith-number/Z63ZQWLVNISXAYMDDDX4E73PPC/graph.json","events_json":"https://pith.science/api/pith-number/Z63ZQWLVNISXAYMDDDX4E73PPC/events.json","paper":"https://pith.science/paper/Z63ZQWLV"},"agent_actions":{"view_html":"https://pith.science/pith/Z63ZQWLVNISXAYMDDDX4E73PPC","download_json":"https://pith.science/pith/Z63ZQWLVNISXAYMDDDX4E73PPC.json","view_paper":"https://pith.science/paper/Z63ZQWLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11124&json=true","fetch_graph":"https://pith.science/api/pith-number/Z63ZQWLVNISXAYMDDDX4E73PPC/graph.json","fetch_events":"https://pith.science/api/pith-number/Z63ZQWLVNISXAYMDDDX4E73PPC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z63ZQWLVNISXAYMDDDX4E73PPC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z63ZQWLVNISXAYMDDDX4E73PPC/action/storage_attestation","attest_author":"https://pith.science/pith/Z63ZQWLVNISXAYMDDDX4E73PPC/action/author_attestation","sign_citation":"https://pith.science/pith/Z63ZQWLVNISXAYMDDDX4E73PPC/action/citation_signature","submit_replication":"https://pith.science/pith/Z63ZQWLVNISXAYMDDDX4E73PPC/action/replication_record"}},"created_at":"2026-07-05T10:56:13.809334+00:00","updated_at":"2026-07-05T10:56:13.809334+00:00"}