{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GZZ7URUPCMU5OLEDIARGVCDLD2","short_pith_number":"pith:GZZ7URUP","schema_version":"1.0","canonical_sha256":"3673fa468f1329d72c8340226a886b1eb4a25fdde53da6a91b88c462ec41e40f","source":{"kind":"arxiv","id":"2505.23524","version":2},"attestation_state":"computed","paper":{"title":"CLIP-AE: CLIP-assisted Cross-view Audio-Visual Enhancement for Unsupervised Temporal Action Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Dan Jiang, Ke Zhang, Quan Zhang, Rui Xia","submitted_at":"2025-05-29T15:03:59Z","abstract_excerpt":"Temporal Action Localization (TAL) has garnered significant attention in information retrieval. Existing supervised or weakly supervised methods heavily rely on labeled temporal boundaries and action categories, which are labor-intensive and time-consuming. Consequently, unsupervised temporal action localization (UTAL) has gained popularity. However, current methods face two main challenges: 1) Classification pre-trained features overly focus on highly discriminative regions; 2) Solely relying on visual modality information makes it difficult to determine contextual boundaries. To address thes"},"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":"2505.23524","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T15:03:59Z","cross_cats_sorted":[],"title_canon_sha256":"1d815796b5a726410821790967ec57dd708b3a13c3095abe9ea730c637a72047","abstract_canon_sha256":"df86fe26d9a15c1b7309bbfbfd95ff35b484a28a950f4bce283224f78f4cf37d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:08.832097Z","signature_b64":"2LZQhg5t7qxU4NcxZUaBLx92c+hSVL3cA05NAvOQfaA+yhAlO+FNjpUS6F5kRa4HreVTS3TIBsdX/XZiuWczCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3673fa468f1329d72c8340226a886b1eb4a25fdde53da6a91b88c462ec41e40f","last_reissued_at":"2026-07-05T11:16:08.831551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:08.831551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP-AE: CLIP-assisted Cross-view Audio-Visual Enhancement for Unsupervised Temporal Action Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Dan Jiang, Ke Zhang, Quan Zhang, Rui Xia","submitted_at":"2025-05-29T15:03:59Z","abstract_excerpt":"Temporal Action Localization (TAL) has garnered significant attention in information retrieval. Existing supervised or weakly supervised methods heavily rely on labeled temporal boundaries and action categories, which are labor-intensive and time-consuming. Consequently, unsupervised temporal action localization (UTAL) has gained popularity. However, current methods face two main challenges: 1) Classification pre-trained features overly focus on highly discriminative regions; 2) Solely relying on visual modality information makes it difficult to determine contextual boundaries. To address thes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23524","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/2505.23524/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":"2505.23524","created_at":"2026-07-05T11:16:08.831617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23524v2","created_at":"2026-07-05T11:16:08.831617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23524","created_at":"2026-07-05T11:16:08.831617+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZZ7URUPCMU5","created_at":"2026-07-05T11:16:08.831617+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZZ7URUPCMU5OLED","created_at":"2026-07-05T11:16:08.831617+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZZ7URUP","created_at":"2026-07-05T11:16:08.831617+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23524","citing_title":"CLIP-AE: CLIP-assisted Cross-view Audio-Visual Enhancement for Unsupervised Temporal Action Localization","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZZ7URUPCMU5OLEDIARGVCDLD2","json":"https://pith.science/pith/GZZ7URUPCMU5OLEDIARGVCDLD2.json","graph_json":"https://pith.science/api/pith-number/GZZ7URUPCMU5OLEDIARGVCDLD2/graph.json","events_json":"https://pith.science/api/pith-number/GZZ7URUPCMU5OLEDIARGVCDLD2/events.json","paper":"https://pith.science/paper/GZZ7URUP"},"agent_actions":{"view_html":"https://pith.science/pith/GZZ7URUPCMU5OLEDIARGVCDLD2","download_json":"https://pith.science/pith/GZZ7URUPCMU5OLEDIARGVCDLD2.json","view_paper":"https://pith.science/paper/GZZ7URUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23524&json=true","fetch_graph":"https://pith.science/api/pith-number/GZZ7URUPCMU5OLEDIARGVCDLD2/graph.json","fetch_events":"https://pith.science/api/pith-number/GZZ7URUPCMU5OLEDIARGVCDLD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZZ7URUPCMU5OLEDIARGVCDLD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZZ7URUPCMU5OLEDIARGVCDLD2/action/storage_attestation","attest_author":"https://pith.science/pith/GZZ7URUPCMU5OLEDIARGVCDLD2/action/author_attestation","sign_citation":"https://pith.science/pith/GZZ7URUPCMU5OLEDIARGVCDLD2/action/citation_signature","submit_replication":"https://pith.science/pith/GZZ7URUPCMU5OLEDIARGVCDLD2/action/replication_record"}},"created_at":"2026-07-05T11:16:08.831617+00:00","updated_at":"2026-07-05T11:16:08.831617+00:00"}