{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:627POE2ZSGSEM7JNGLLC62COAU","short_pith_number":"pith:627POE2Z","schema_version":"1.0","canonical_sha256":"f6bef7135991a4467d2d32d62f684e0525e71be2076211cf1baf76254029e65e","source":{"kind":"arxiv","id":"2203.05114","version":1},"attestation_state":"computed","paper":{"title":"OpenTAL: Towards Open Set Temporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qi Yu, Wentao Bao, Yu Kong","submitted_at":"2022-03-10T02:18:39Z","abstract_excerpt":"Temporal Action Localization (TAL) has experienced remarkable success under the supervised learning paradigm. However, existing TAL methods are rooted in the closed set assumption, which cannot handle the inevitable unknown actions in open-world scenarios. In this paper, we, for the first time, step toward the Open Set TAL (OSTAL) problem and propose a general framework OpenTAL based on Evidential Deep Learning (EDL). Specifically, the OpenTAL consists of uncertainty-aware action classification, actionness prediction, and temporal location regression. With the proposed importance-balanced EDL "},"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":"2203.05114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-10T02:18:39Z","cross_cats_sorted":[],"title_canon_sha256":"e373717d83c10dc79b2acfd94edf4350e968976d529dbf59cb702c1e52f69314","abstract_canon_sha256":"95df2a4ee96c44a3adc2a28c1466d9b5608884b7177f9c5047f71e3680557b29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:03:30.086224Z","signature_b64":"byhRGk6DwiG643ygMDN/PGXNJBkWlhEXxeIyvY2prro2c+j6/ssQOIVLNwZuVz4livD2jCNHF600yAoM5HmeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6bef7135991a4467d2d32d62f684e0525e71be2076211cf1baf76254029e65e","last_reissued_at":"2026-07-05T04:03:30.085881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:03:30.085881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenTAL: Towards Open Set Temporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qi Yu, Wentao Bao, Yu Kong","submitted_at":"2022-03-10T02:18:39Z","abstract_excerpt":"Temporal Action Localization (TAL) has experienced remarkable success under the supervised learning paradigm. However, existing TAL methods are rooted in the closed set assumption, which cannot handle the inevitable unknown actions in open-world scenarios. In this paper, we, for the first time, step toward the Open Set TAL (OSTAL) problem and propose a general framework OpenTAL based on Evidential Deep Learning (EDL). Specifically, the OpenTAL consists of uncertainty-aware action classification, actionness prediction, and temporal location regression. With the proposed importance-balanced EDL "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.05114","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/2203.05114/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":"2203.05114","created_at":"2026-07-05T04:03:30.085940+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.05114v1","created_at":"2026-07-05T04:03:30.085940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.05114","created_at":"2026-07-05T04:03:30.085940+00:00"},{"alias_kind":"pith_short_12","alias_value":"627POE2ZSGSE","created_at":"2026-07-05T04:03:30.085940+00:00"},{"alias_kind":"pith_short_16","alias_value":"627POE2ZSGSEM7JN","created_at":"2026-07-05T04:03:30.085940+00:00"},{"alias_kind":"pith_short_8","alias_value":"627POE2Z","created_at":"2026-07-05T04:03:30.085940+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06032","citing_title":"Ensemble-Based Dirichlet Modeling for Predictive Uncertainty and Selective Classification","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/627POE2ZSGSEM7JNGLLC62COAU","json":"https://pith.science/pith/627POE2ZSGSEM7JNGLLC62COAU.json","graph_json":"https://pith.science/api/pith-number/627POE2ZSGSEM7JNGLLC62COAU/graph.json","events_json":"https://pith.science/api/pith-number/627POE2ZSGSEM7JNGLLC62COAU/events.json","paper":"https://pith.science/paper/627POE2Z"},"agent_actions":{"view_html":"https://pith.science/pith/627POE2ZSGSEM7JNGLLC62COAU","download_json":"https://pith.science/pith/627POE2ZSGSEM7JNGLLC62COAU.json","view_paper":"https://pith.science/paper/627POE2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.05114&json=true","fetch_graph":"https://pith.science/api/pith-number/627POE2ZSGSEM7JNGLLC62COAU/graph.json","fetch_events":"https://pith.science/api/pith-number/627POE2ZSGSEM7JNGLLC62COAU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/627POE2ZSGSEM7JNGLLC62COAU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/627POE2ZSGSEM7JNGLLC62COAU/action/storage_attestation","attest_author":"https://pith.science/pith/627POE2ZSGSEM7JNGLLC62COAU/action/author_attestation","sign_citation":"https://pith.science/pith/627POE2ZSGSEM7JNGLLC62COAU/action/citation_signature","submit_replication":"https://pith.science/pith/627POE2ZSGSEM7JNGLLC62COAU/action/replication_record"}},"created_at":"2026-07-05T04:03:30.085940+00:00","updated_at":"2026-07-05T04:03:30.085940+00:00"}