{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZBQ5XTLMYNTVLLBXRTMGABHMHG","short_pith_number":"pith:ZBQ5XTLM","schema_version":"1.0","canonical_sha256":"c861dbcd6cc36755ac378cd86004ec39ab84dfa3d38d69a012692f97a08aba7f","source":{"kind":"arxiv","id":"2304.02934","version":1},"attestation_state":"computed","paper":{"title":"Boundary-Denoising for Video Activity Localization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernard Ghanem, Jialin Gao, Juan-Manuel P\\'erez-R\\'ua, Mattia Soldan, Mengmeng Xu, Shuming Liu","submitted_at":"2023-04-06T08:48:01Z","abstract_excerpt":"Video activity localization aims at understanding the semantic content in long untrimmed videos and retrieving actions of interest. The retrieved action with its start and end locations can be used for highlight generation, temporal action detection, etc. Unfortunately, learning the exact boundary location of activities is highly challenging because temporal activities are continuous in time, and there are often no clear-cut transitions between actions. Moreover, the definition of the start and end of events is subjective, which may confuse the model. To alleviate the boundary ambiguity, we pr"},"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":"2304.02934","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T08:48:01Z","cross_cats_sorted":[],"title_canon_sha256":"0cf3751cfbd26dbcfe82589623034430c20d11411f57e5ddbafb82ae96ac3167","abstract_canon_sha256":"424f64347e81b7b5d9f6535f26e81495f1a847fdb474dc7edfbcb5c7d89f58f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:43.239385Z","signature_b64":"pkZoUEz1b1bWEAazzo2+4/s7EVawmCAcmZuOiyQ3GPDfk+dDQzTfdSsNHQ+jd/M4BBY1BqtjjSIBIG+RJQVBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c861dbcd6cc36755ac378cd86004ec39ab84dfa3d38d69a012692f97a08aba7f","last_reissued_at":"2026-07-05T05:58:43.239021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:43.239021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boundary-Denoising for Video Activity Localization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernard Ghanem, Jialin Gao, Juan-Manuel P\\'erez-R\\'ua, Mattia Soldan, Mengmeng Xu, Shuming Liu","submitted_at":"2023-04-06T08:48:01Z","abstract_excerpt":"Video activity localization aims at understanding the semantic content in long untrimmed videos and retrieving actions of interest. The retrieved action with its start and end locations can be used for highlight generation, temporal action detection, etc. Unfortunately, learning the exact boundary location of activities is highly challenging because temporal activities are continuous in time, and there are often no clear-cut transitions between actions. Moreover, the definition of the start and end of events is subjective, which may confuse the model. To alleviate the boundary ambiguity, we pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02934","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/2304.02934/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":"2304.02934","created_at":"2026-07-05T05:58:43.239082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.02934v1","created_at":"2026-07-05T05:58:43.239082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02934","created_at":"2026-07-05T05:58:43.239082+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBQ5XTLMYNTV","created_at":"2026-07-05T05:58:43.239082+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBQ5XTLMYNTVLLBX","created_at":"2026-07-05T05:58:43.239082+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBQ5XTLM","created_at":"2026-07-05T05:58:43.239082+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.07157","citing_title":"Multi-Scale Contrastive Learning for Video Temporal Grounding","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZBQ5XTLMYNTVLLBXRTMGABHMHG","json":"https://pith.science/pith/ZBQ5XTLMYNTVLLBXRTMGABHMHG.json","graph_json":"https://pith.science/api/pith-number/ZBQ5XTLMYNTVLLBXRTMGABHMHG/graph.json","events_json":"https://pith.science/api/pith-number/ZBQ5XTLMYNTVLLBXRTMGABHMHG/events.json","paper":"https://pith.science/paper/ZBQ5XTLM"},"agent_actions":{"view_html":"https://pith.science/pith/ZBQ5XTLMYNTVLLBXRTMGABHMHG","download_json":"https://pith.science/pith/ZBQ5XTLMYNTVLLBXRTMGABHMHG.json","view_paper":"https://pith.science/paper/ZBQ5XTLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.02934&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBQ5XTLMYNTVLLBXRTMGABHMHG/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBQ5XTLMYNTVLLBXRTMGABHMHG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBQ5XTLMYNTVLLBXRTMGABHMHG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBQ5XTLMYNTVLLBXRTMGABHMHG/action/storage_attestation","attest_author":"https://pith.science/pith/ZBQ5XTLMYNTVLLBXRTMGABHMHG/action/author_attestation","sign_citation":"https://pith.science/pith/ZBQ5XTLMYNTVLLBXRTMGABHMHG/action/citation_signature","submit_replication":"https://pith.science/pith/ZBQ5XTLMYNTVLLBXRTMGABHMHG/action/replication_record"}},"created_at":"2026-07-05T05:58:43.239082+00:00","updated_at":"2026-07-05T05:58:43.239082+00:00"}