{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VHGIBIBFRZHYBVSIXEUEJTYSUS","short_pith_number":"pith:VHGIBIBF","schema_version":"1.0","canonical_sha256":"a9cc80a0258e4f80d648b92844cf12a48a9f8000e95eeae9c1d1b9dacc52cef6","source":{"kind":"arxiv","id":"2208.07493","version":1},"attestation_state":"computed","paper":{"title":"Temporal Action Localization with Multi-temporal Scales","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"An-An Liu, Meng Wang, Shenyong Chen, Tao Zhuo, Xinglei Cui, Zan Gao, Zhiyong Cheng","submitted_at":"2022-08-16T01:48:23Z","abstract_excerpt":"Temporal action localization plays an important role in video analysis, which aims to localize and classify actions in untrimmed videos. The previous methods often predict actions on a feature space of a single-temporal scale. However, the temporal features of a low-level scale lack enough semantics for action classification while a high-level scale cannot provide rich details of the action boundaries. To address this issue, we propose to predict actions on a feature space of multi-temporal scales. Specifically, we use refined feature pyramids of different scales to pass semantics from high-le"},"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":"2208.07493","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-16T01:48:23Z","cross_cats_sorted":[],"title_canon_sha256":"e079d772062069169d7dd7107c237b1c58230550d64c874f8d4717eb1e5df1f1","abstract_canon_sha256":"b47ecb5c8128bbb72af38e3b59c783041e8ba0e02e324babc3cb18119e4053f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:49:05.392100Z","signature_b64":"TDVgNu7fXe00bgZ6m+30lQ+BgoFBE4CPGuLh+UScP31JQM5nBDl7yqd+Eyhgj9SWwze2Dl8XPoja4d9DcDrXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9cc80a0258e4f80d648b92844cf12a48a9f8000e95eeae9c1d1b9dacc52cef6","last_reissued_at":"2026-07-05T04:49:05.391680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:49:05.391680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal Action Localization with Multi-temporal Scales","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"An-An Liu, Meng Wang, Shenyong Chen, Tao Zhuo, Xinglei Cui, Zan Gao, Zhiyong Cheng","submitted_at":"2022-08-16T01:48:23Z","abstract_excerpt":"Temporal action localization plays an important role in video analysis, which aims to localize and classify actions in untrimmed videos. The previous methods often predict actions on a feature space of a single-temporal scale. However, the temporal features of a low-level scale lack enough semantics for action classification while a high-level scale cannot provide rich details of the action boundaries. To address this issue, we propose to predict actions on a feature space of multi-temporal scales. Specifically, we use refined feature pyramids of different scales to pass semantics from high-le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.07493","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/2208.07493/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":"2208.07493","created_at":"2026-07-05T04:49:05.391740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.07493v1","created_at":"2026-07-05T04:49:05.391740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.07493","created_at":"2026-07-05T04:49:05.391740+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHGIBIBFRZHY","created_at":"2026-07-05T04:49:05.391740+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHGIBIBFRZHYBVSI","created_at":"2026-07-05T04:49:05.391740+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHGIBIBF","created_at":"2026-07-05T04:49:05.391740+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06411","citing_title":"Hierarchical Multi-Stage Transformer Architecture for Context-Aware Temporal Action Localization","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VHGIBIBFRZHYBVSIXEUEJTYSUS","json":"https://pith.science/pith/VHGIBIBFRZHYBVSIXEUEJTYSUS.json","graph_json":"https://pith.science/api/pith-number/VHGIBIBFRZHYBVSIXEUEJTYSUS/graph.json","events_json":"https://pith.science/api/pith-number/VHGIBIBFRZHYBVSIXEUEJTYSUS/events.json","paper":"https://pith.science/paper/VHGIBIBF"},"agent_actions":{"view_html":"https://pith.science/pith/VHGIBIBFRZHYBVSIXEUEJTYSUS","download_json":"https://pith.science/pith/VHGIBIBFRZHYBVSIXEUEJTYSUS.json","view_paper":"https://pith.science/paper/VHGIBIBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.07493&json=true","fetch_graph":"https://pith.science/api/pith-number/VHGIBIBFRZHYBVSIXEUEJTYSUS/graph.json","fetch_events":"https://pith.science/api/pith-number/VHGIBIBFRZHYBVSIXEUEJTYSUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHGIBIBFRZHYBVSIXEUEJTYSUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHGIBIBFRZHYBVSIXEUEJTYSUS/action/storage_attestation","attest_author":"https://pith.science/pith/VHGIBIBFRZHYBVSIXEUEJTYSUS/action/author_attestation","sign_citation":"https://pith.science/pith/VHGIBIBFRZHYBVSIXEUEJTYSUS/action/citation_signature","submit_replication":"https://pith.science/pith/VHGIBIBFRZHYBVSIXEUEJTYSUS/action/replication_record"}},"created_at":"2026-07-05T04:49:05.391740+00:00","updated_at":"2026-07-05T04:49:05.391740+00:00"}