{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IDB27Q7CGADYV4G6KK36WNFW3Z","short_pith_number":"pith:IDB27Q7C","schema_version":"1.0","canonical_sha256":"40c3afc3e230078af0de52b7eb34b6de72a1bacc608ec4cc305c21c221fd0cef","source":{"kind":"arxiv","id":"2203.13609","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Pre-training for Temporal Action Localization Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Zhang, Jue Wang, Junwu Weng, Meng Cao, Tianyu Yang, Yuexian Zou","submitted_at":"2022-03-25T12:13:43Z","abstract_excerpt":"Unsupervised video representation learning has made remarkable achievements in recent years. However, most existing methods are designed and optimized for video classification. These pre-trained models can be sub-optimal for temporal localization tasks due to the inherent discrepancy between video-level classification and clip-level localization. To bridge this gap, we make the first attempt to propose a self-supervised pretext task, coined as Pseudo Action Localization (PAL) to Unsupervisedly Pre-train feature encoders for Temporal Action Localization tasks (UP-TAL). Specifically, we first ra"},"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":"2203.13609","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-25T12:13:43Z","cross_cats_sorted":[],"title_canon_sha256":"5d402d568ea575e47498770d70cf553d23bd6b44d246bcd55fb5792dd293eb5b","abstract_canon_sha256":"dc2d69b4241947f4cb4bab9f0eccdcb17c9dcf21123c197fc8620a9a44105112"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:34.565515Z","signature_b64":"pC6lHLqFfoTiUB9xJC+zw4VlN9RyAwihifSiH75e+XR/9c/GMvEYZQTi90Bnyfci344wtI2ZlC6Zqoj5Q5XrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40c3afc3e230078af0de52b7eb34b6de72a1bacc608ec4cc305c21c221fd0cef","last_reissued_at":"2026-07-05T04:08:34.565102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:34.565102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Pre-training for Temporal Action Localization Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Zhang, Jue Wang, Junwu Weng, Meng Cao, Tianyu Yang, Yuexian Zou","submitted_at":"2022-03-25T12:13:43Z","abstract_excerpt":"Unsupervised video representation learning has made remarkable achievements in recent years. However, most existing methods are designed and optimized for video classification. These pre-trained models can be sub-optimal for temporal localization tasks due to the inherent discrepancy between video-level classification and clip-level localization. To bridge this gap, we make the first attempt to propose a self-supervised pretext task, coined as Pseudo Action Localization (PAL) to Unsupervisedly Pre-train feature encoders for Temporal Action Localization tasks (UP-TAL). Specifically, we first ra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13609","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/2203.13609/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":"2203.13609","created_at":"2026-07-05T04:08:34.565158+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.13609v1","created_at":"2026-07-05T04:08:34.565158+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13609","created_at":"2026-07-05T04:08:34.565158+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDB27Q7CGADY","created_at":"2026-07-05T04:08:34.565158+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDB27Q7CGADYV4G6","created_at":"2026-07-05T04:08:34.565158+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDB27Q7C","created_at":"2026-07-05T04:08:34.565158+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/IDB27Q7CGADYV4G6KK36WNFW3Z","json":"https://pith.science/pith/IDB27Q7CGADYV4G6KK36WNFW3Z.json","graph_json":"https://pith.science/api/pith-number/IDB27Q7CGADYV4G6KK36WNFW3Z/graph.json","events_json":"https://pith.science/api/pith-number/IDB27Q7CGADYV4G6KK36WNFW3Z/events.json","paper":"https://pith.science/paper/IDB27Q7C"},"agent_actions":{"view_html":"https://pith.science/pith/IDB27Q7CGADYV4G6KK36WNFW3Z","download_json":"https://pith.science/pith/IDB27Q7CGADYV4G6KK36WNFW3Z.json","view_paper":"https://pith.science/paper/IDB27Q7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.13609&json=true","fetch_graph":"https://pith.science/api/pith-number/IDB27Q7CGADYV4G6KK36WNFW3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/IDB27Q7CGADYV4G6KK36WNFW3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDB27Q7CGADYV4G6KK36WNFW3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDB27Q7CGADYV4G6KK36WNFW3Z/action/storage_attestation","attest_author":"https://pith.science/pith/IDB27Q7CGADYV4G6KK36WNFW3Z/action/author_attestation","sign_citation":"https://pith.science/pith/IDB27Q7CGADYV4G6KK36WNFW3Z/action/citation_signature","submit_replication":"https://pith.science/pith/IDB27Q7CGADYV4G6KK36WNFW3Z/action/replication_record"}},"created_at":"2026-07-05T04:08:34.565158+00:00","updated_at":"2026-07-05T04:08:34.565158+00:00"}