{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XCNSMZOX4DWJP3JI34KT3PMNR7","short_pith_number":"pith:XCNSMZOX","schema_version":"1.0","canonical_sha256":"b89b2665d7e0ec97ed28df153dbd8d8ff5a84d294755533c9bad727692f20055","source":{"kind":"arxiv","id":"2411.11278","version":3},"attestation_state":"computed","paper":{"title":"Towards Open-Vocabulary Audio-Visual Event Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Dan Guo, Jingjing Hu, Jinxing Zhou, Meng Wang, Ruohao Guo, Xiaojun Chang, Yiran Zhong, Yuxin Mao","submitted_at":"2024-11-18T04:35:20Z","abstract_excerpt":"The Audio-Visual Event Localization (AVEL) task aims to temporally locate and classify video events that are both audible and visible. Most research in this field assumes a closed-set setting, which restricts these models' ability to handle test data containing event categories absent (unseen) during training. Recently, a few studies have explored AVEL in an open-set setting, enabling the recognition of unseen events as ``unknown'', but without providing category-specific semantics. In this paper, we advance the field by introducing the Open-Vocabulary Audio-Visual Event Localization (OV-AVEL)"},"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":"2411.11278","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-18T04:35:20Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"e9f5590f5282cd0f1e95364667c12c22da092e61e7689949776b888bf00e1552","abstract_canon_sha256":"00db3541f7d980a60dfb4d06295a2d72a1ccb0bc680b69967c3de9f5c1a05a8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:26.460998Z","signature_b64":"aBKthAf+ng7H0McQrIIJYCgO0iDtQvMxrYmGALMYc/oSzioSPnriySPvO7ObaeHWcJEZ1W6OO4eEZ0+nhQ0kCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b89b2665d7e0ec97ed28df153dbd8d8ff5a84d294755533c9bad727692f20055","last_reissued_at":"2026-07-05T10:28:26.460490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:26.460490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Open-Vocabulary Audio-Visual Event Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Dan Guo, Jingjing Hu, Jinxing Zhou, Meng Wang, Ruohao Guo, Xiaojun Chang, Yiran Zhong, Yuxin Mao","submitted_at":"2024-11-18T04:35:20Z","abstract_excerpt":"The Audio-Visual Event Localization (AVEL) task aims to temporally locate and classify video events that are both audible and visible. Most research in this field assumes a closed-set setting, which restricts these models' ability to handle test data containing event categories absent (unseen) during training. Recently, a few studies have explored AVEL in an open-set setting, enabling the recognition of unseen events as ``unknown'', but without providing category-specific semantics. In this paper, we advance the field by introducing the Open-Vocabulary Audio-Visual Event Localization (OV-AVEL)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11278","kind":"arxiv","version":3},"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/2411.11278/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":"2411.11278","created_at":"2026-07-05T10:28:26.460567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11278v3","created_at":"2026-07-05T10:28:26.460567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11278","created_at":"2026-07-05T10:28:26.460567+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCNSMZOX4DWJ","created_at":"2026-07-05T10:28:26.460567+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCNSMZOX4DWJP3JI","created_at":"2026-07-05T10:28:26.460567+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCNSMZOX","created_at":"2026-07-05T10:28:26.460567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12628","citing_title":"Dense Audio-Visual Event Localization under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XCNSMZOX4DWJP3JI34KT3PMNR7","json":"https://pith.science/pith/XCNSMZOX4DWJP3JI34KT3PMNR7.json","graph_json":"https://pith.science/api/pith-number/XCNSMZOX4DWJP3JI34KT3PMNR7/graph.json","events_json":"https://pith.science/api/pith-number/XCNSMZOX4DWJP3JI34KT3PMNR7/events.json","paper":"https://pith.science/paper/XCNSMZOX"},"agent_actions":{"view_html":"https://pith.science/pith/XCNSMZOX4DWJP3JI34KT3PMNR7","download_json":"https://pith.science/pith/XCNSMZOX4DWJP3JI34KT3PMNR7.json","view_paper":"https://pith.science/paper/XCNSMZOX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11278&json=true","fetch_graph":"https://pith.science/api/pith-number/XCNSMZOX4DWJP3JI34KT3PMNR7/graph.json","fetch_events":"https://pith.science/api/pith-number/XCNSMZOX4DWJP3JI34KT3PMNR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCNSMZOX4DWJP3JI34KT3PMNR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCNSMZOX4DWJP3JI34KT3PMNR7/action/storage_attestation","attest_author":"https://pith.science/pith/XCNSMZOX4DWJP3JI34KT3PMNR7/action/author_attestation","sign_citation":"https://pith.science/pith/XCNSMZOX4DWJP3JI34KT3PMNR7/action/citation_signature","submit_replication":"https://pith.science/pith/XCNSMZOX4DWJP3JI34KT3PMNR7/action/replication_record"}},"created_at":"2026-07-05T10:28:26.460567+00:00","updated_at":"2026-07-05T10:28:26.460567+00:00"}