{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BNVGQSSWAOEBICJLVN4UZ55VRW","short_pith_number":"pith:BNVGQSSW","schema_version":"1.0","canonical_sha256":"0b6a684a56038814092bab794cf7b58d8f494d0c5b407bcb2652fa6435f81c9a","source":{"kind":"arxiv","id":"2409.07967","version":4},"attestation_state":"computed","paper":{"title":"Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyu Qu, Jinhui Tang, Ling Xing, Rui Yan, Xiangbo Shu","submitted_at":"2024-09-12T11:54:25Z","abstract_excerpt":"Dense-localization Audio-Visual Events (DAVE) aims to identify time boundaries and corresponding categories for events that are both audible and visible in a long video, where events may co-occur and exhibit varying durations. However, complex audio-visual scenes often involve asynchronization between modalities, making accurate localization challenging. Existing DAVE solutions extract audio and visual features through unimodal encoders, and fuse them via dense cross-modal interaction. However, independent unimodal encoding struggles to emphasize shared semantics between modalities without cro"},"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":"2409.07967","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T11:54:25Z","cross_cats_sorted":[],"title_canon_sha256":"82af6d227835fc5e0fa96c46a24e641e736012f232ce67ebfc26c95a70be070c","abstract_canon_sha256":"359a250d593970f707854d55f6047a7818b90f602672962f30a471fbdeaf4762"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:38.942597Z","signature_b64":"M1ABF5lnRnc21eMJqbGzDpAVE6ZVKjRzzYsCUokA6Q36c+tj0kg0dJCNpHIx3Ah9GZnAQUrG7by+ao5++9jPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b6a684a56038814092bab794cf7b58d8f494d0c5b407bcb2652fa6435f81c9a","last_reissued_at":"2026-07-05T11:00:38.941944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:38.941944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyu Qu, Jinhui Tang, Ling Xing, Rui Yan, Xiangbo Shu","submitted_at":"2024-09-12T11:54:25Z","abstract_excerpt":"Dense-localization Audio-Visual Events (DAVE) aims to identify time boundaries and corresponding categories for events that are both audible and visible in a long video, where events may co-occur and exhibit varying durations. However, complex audio-visual scenes often involve asynchronization between modalities, making accurate localization challenging. Existing DAVE solutions extract audio and visual features through unimodal encoders, and fuse them via dense cross-modal interaction. However, independent unimodal encoding struggles to emphasize shared semantics between modalities without cro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07967","kind":"arxiv","version":4},"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/2409.07967/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":"2409.07967","created_at":"2026-07-05T11:00:38.942029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07967v4","created_at":"2026-07-05T11:00:38.942029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07967","created_at":"2026-07-05T11:00:38.942029+00:00"},{"alias_kind":"pith_short_12","alias_value":"BNVGQSSWAOEB","created_at":"2026-07-05T11:00:38.942029+00:00"},{"alias_kind":"pith_short_16","alias_value":"BNVGQSSWAOEBICJL","created_at":"2026-07-05T11:00:38.942029+00:00"},{"alias_kind":"pith_short_8","alias_value":"BNVGQSSW","created_at":"2026-07-05T11:00:38.942029+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08723","citing_title":"EAR: Enhancing Uni-Modal Representations for Weakly Supervised Audio-Visual Video Parsing","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BNVGQSSWAOEBICJLVN4UZ55VRW","json":"https://pith.science/pith/BNVGQSSWAOEBICJLVN4UZ55VRW.json","graph_json":"https://pith.science/api/pith-number/BNVGQSSWAOEBICJLVN4UZ55VRW/graph.json","events_json":"https://pith.science/api/pith-number/BNVGQSSWAOEBICJLVN4UZ55VRW/events.json","paper":"https://pith.science/paper/BNVGQSSW"},"agent_actions":{"view_html":"https://pith.science/pith/BNVGQSSWAOEBICJLVN4UZ55VRW","download_json":"https://pith.science/pith/BNVGQSSWAOEBICJLVN4UZ55VRW.json","view_paper":"https://pith.science/paper/BNVGQSSW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07967&json=true","fetch_graph":"https://pith.science/api/pith-number/BNVGQSSWAOEBICJLVN4UZ55VRW/graph.json","fetch_events":"https://pith.science/api/pith-number/BNVGQSSWAOEBICJLVN4UZ55VRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BNVGQSSWAOEBICJLVN4UZ55VRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BNVGQSSWAOEBICJLVN4UZ55VRW/action/storage_attestation","attest_author":"https://pith.science/pith/BNVGQSSWAOEBICJLVN4UZ55VRW/action/author_attestation","sign_citation":"https://pith.science/pith/BNVGQSSWAOEBICJLVN4UZ55VRW/action/citation_signature","submit_replication":"https://pith.science/pith/BNVGQSSWAOEBICJLVN4UZ55VRW/action/replication_record"}},"created_at":"2026-07-05T11:00:38.942029+00:00","updated_at":"2026-07-05T11:00:38.942029+00:00"}