{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZA4SA3DVQWRXC47SLEHSXAX4PQ","short_pith_number":"pith:ZA4SA3DV","schema_version":"1.0","canonical_sha256":"c839206c7585a37173f2590f2b82fc7c03baf1740eb3f769bbdde19790096c87","source":{"kind":"arxiv","id":"2310.03456","version":1},"attestation_state":"computed","paper":{"title":"Multi-Resolution Audio-Visual Feature Fusion for Temporal Action Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Andrew Gilbert, Edward Fish, Jon Weinbren","submitted_at":"2023-10-05T10:54:33Z","abstract_excerpt":"Temporal Action Localization (TAL) aims to identify actions' start, end, and class labels in untrimmed videos. While recent advancements using transformer networks and Feature Pyramid Networks (FPN) have enhanced visual feature recognition in TAL tasks, less progress has been made in the integration of audio features into such frameworks. This paper introduces the Multi-Resolution Audio-Visual Feature Fusion (MRAV-FF), an innovative method to merge audio-visual data across different temporal resolutions. Central to our approach is a hierarchical gated cross-attention mechanism, which discernin"},"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":"2310.03456","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-05T10:54:33Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"d8e579af6c72209c13dd02a8419189388ed6d28bba4659aa72ae4814fe7df65c","abstract_canon_sha256":"db61dc8477754aae77c1a2664742acbd712cd3bf30a4ef91585956ac320c42ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:33.877463Z","signature_b64":"SZDCJ3aeRXMXncdfOI0fCWFawtQdS24nfM8GkkZY/WD+DHnGnwMgWlgHe1Sg/g/rm+0rLF/n7SE2LvLo8kusBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c839206c7585a37173f2590f2b82fc7c03baf1740eb3f769bbdde19790096c87","last_reissued_at":"2026-07-05T06:57:33.876936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:33.876936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Resolution Audio-Visual Feature Fusion for Temporal Action Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Andrew Gilbert, Edward Fish, Jon Weinbren","submitted_at":"2023-10-05T10:54:33Z","abstract_excerpt":"Temporal Action Localization (TAL) aims to identify actions' start, end, and class labels in untrimmed videos. While recent advancements using transformer networks and Feature Pyramid Networks (FPN) have enhanced visual feature recognition in TAL tasks, less progress has been made in the integration of audio features into such frameworks. This paper introduces the Multi-Resolution Audio-Visual Feature Fusion (MRAV-FF), an innovative method to merge audio-visual data across different temporal resolutions. Central to our approach is a hierarchical gated cross-attention mechanism, which discernin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03456","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/2310.03456/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":"2310.03456","created_at":"2026-07-05T06:57:33.877002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.03456v1","created_at":"2026-07-05T06:57:33.877002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03456","created_at":"2026-07-05T06:57:33.877002+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZA4SA3DVQWRX","created_at":"2026-07-05T06:57:33.877002+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZA4SA3DVQWRXC47S","created_at":"2026-07-05T06:57:33.877002+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZA4SA3DV","created_at":"2026-07-05T06:57:33.877002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23196","citing_title":"DEL: Dense Event Localization for Multi-modal Audio-Visual Understanding","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZA4SA3DVQWRXC47SLEHSXAX4PQ","json":"https://pith.science/pith/ZA4SA3DVQWRXC47SLEHSXAX4PQ.json","graph_json":"https://pith.science/api/pith-number/ZA4SA3DVQWRXC47SLEHSXAX4PQ/graph.json","events_json":"https://pith.science/api/pith-number/ZA4SA3DVQWRXC47SLEHSXAX4PQ/events.json","paper":"https://pith.science/paper/ZA4SA3DV"},"agent_actions":{"view_html":"https://pith.science/pith/ZA4SA3DVQWRXC47SLEHSXAX4PQ","download_json":"https://pith.science/pith/ZA4SA3DVQWRXC47SLEHSXAX4PQ.json","view_paper":"https://pith.science/paper/ZA4SA3DV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.03456&json=true","fetch_graph":"https://pith.science/api/pith-number/ZA4SA3DVQWRXC47SLEHSXAX4PQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZA4SA3DVQWRXC47SLEHSXAX4PQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZA4SA3DVQWRXC47SLEHSXAX4PQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZA4SA3DVQWRXC47SLEHSXAX4PQ/action/storage_attestation","attest_author":"https://pith.science/pith/ZA4SA3DVQWRXC47SLEHSXAX4PQ/action/author_attestation","sign_citation":"https://pith.science/pith/ZA4SA3DVQWRXC47SLEHSXAX4PQ/action/citation_signature","submit_replication":"https://pith.science/pith/ZA4SA3DVQWRXC47SLEHSXAX4PQ/action/replication_record"}},"created_at":"2026-07-05T06:57:33.877002+00:00","updated_at":"2026-07-05T06:57:33.877002+00:00"}