{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GDNUGN44CQJEBIGU3FSWXVDO3I","short_pith_number":"pith:GDNUGN44","schema_version":"1.0","canonical_sha256":"30db43379c141240a0d4d9656bd46eda0274ccbbdc5642e05fadeacfadd3c366","source":{"kind":"arxiv","id":"2506.23196","version":1},"attestation_state":"computed","paper":{"title":"DEL: Dense Event Localization for Multi-modal Audio-Visual Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amir Shirian, Andrew Gilbert, Frank Guerin, Mona Ahmadian","submitted_at":"2025-06-29T11:50:19Z","abstract_excerpt":"Real-world videos often contain overlapping events and complex temporal dependencies, making multimodal interaction modeling particularly challenging. We introduce DEL, a framework for dense semantic action localization, aiming to accurately detect and classify multiple actions at fine-grained temporal resolutions in long untrimmed videos. DEL consists of two key modules: the alignment of audio and visual features that leverage masked self-attention to enhance intra-mode consistency and a multimodal interaction refinement module that models cross-modal dependencies across multiple scales, enab"},"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":"2506.23196","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T11:50:19Z","cross_cats_sorted":[],"title_canon_sha256":"adeba99197e9a865245fdf4a84a59cce122a649a26d342b836b92cb6e11ed505","abstract_canon_sha256":"fd9f01f13dbd072da8a757b8a4dcacc3805efb347fc962264219072ad190a809"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:17.531032Z","signature_b64":"hkJDLeBzTbx/MEscA1eGLlkf8Xdf2FnNHqfp3Xa2zh1N5s9fQWmrSaMCgg1suVkABQxLEaOipYpENeCDWgfeCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30db43379c141240a0d4d9656bd46eda0274ccbbdc5642e05fadeacfadd3c366","last_reissued_at":"2026-07-05T11:29:17.530532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:17.530532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DEL: Dense Event Localization for Multi-modal Audio-Visual Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amir Shirian, Andrew Gilbert, Frank Guerin, Mona Ahmadian","submitted_at":"2025-06-29T11:50:19Z","abstract_excerpt":"Real-world videos often contain overlapping events and complex temporal dependencies, making multimodal interaction modeling particularly challenging. We introduce DEL, a framework for dense semantic action localization, aiming to accurately detect and classify multiple actions at fine-grained temporal resolutions in long untrimmed videos. DEL consists of two key modules: the alignment of audio and visual features that leverage masked self-attention to enhance intra-mode consistency and a multimodal interaction refinement module that models cross-modal dependencies across multiple scales, enab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23196","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/2506.23196/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":"2506.23196","created_at":"2026-07-05T11:29:17.530593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23196v1","created_at":"2026-07-05T11:29:17.530593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23196","created_at":"2026-07-05T11:29:17.530593+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDNUGN44CQJE","created_at":"2026-07-05T11:29:17.530593+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDNUGN44CQJEBIGU","created_at":"2026-07-05T11:29:17.530593+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDNUGN44","created_at":"2026-07-05T11:29:17.530593+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":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GDNUGN44CQJEBIGU3FSWXVDO3I","json":"https://pith.science/pith/GDNUGN44CQJEBIGU3FSWXVDO3I.json","graph_json":"https://pith.science/api/pith-number/GDNUGN44CQJEBIGU3FSWXVDO3I/graph.json","events_json":"https://pith.science/api/pith-number/GDNUGN44CQJEBIGU3FSWXVDO3I/events.json","paper":"https://pith.science/paper/GDNUGN44"},"agent_actions":{"view_html":"https://pith.science/pith/GDNUGN44CQJEBIGU3FSWXVDO3I","download_json":"https://pith.science/pith/GDNUGN44CQJEBIGU3FSWXVDO3I.json","view_paper":"https://pith.science/paper/GDNUGN44","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23196&json=true","fetch_graph":"https://pith.science/api/pith-number/GDNUGN44CQJEBIGU3FSWXVDO3I/graph.json","fetch_events":"https://pith.science/api/pith-number/GDNUGN44CQJEBIGU3FSWXVDO3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDNUGN44CQJEBIGU3FSWXVDO3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDNUGN44CQJEBIGU3FSWXVDO3I/action/storage_attestation","attest_author":"https://pith.science/pith/GDNUGN44CQJEBIGU3FSWXVDO3I/action/author_attestation","sign_citation":"https://pith.science/pith/GDNUGN44CQJEBIGU3FSWXVDO3I/action/citation_signature","submit_replication":"https://pith.science/pith/GDNUGN44CQJEBIGU3FSWXVDO3I/action/replication_record"}},"created_at":"2026-07-05T11:29:17.530593+00:00","updated_at":"2026-07-05T11:29:17.530593+00:00"}