{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3N6AN3BJHOPQRJWQO7DKKXZZFS","short_pith_number":"pith:3N6AN3BJ","schema_version":"1.0","canonical_sha256":"db7c06ec293b9f08a6d077c6a55f392caddfffa2add8a0ce403005ad83dbcf53","source":{"kind":"arxiv","id":"2406.08771","version":2},"attestation_state":"computed","paper":{"title":"MFF-EINV2: Multi-scale Feature Fusion across Spectral-Spatial-Temporal Domains for Sound Event Localization and Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Da Mu, Haobo Yue, Zhicheng Zhang","submitted_at":"2024-06-13T03:03:02Z","abstract_excerpt":"Sound Event Localization and Detection (SELD) involves detecting and localizing sound events using multichannel sound recordings. Previously proposed Event-Independent Network V2 (EINV2) has achieved outstanding performance on SELD. However, it still faces challenges in effectively extracting features across spectral, spatial, and temporal domains. This paper proposes a three-stage network structure named Multi-scale Feature Fusion (MFF) module to fully extract multi-scale features across spectral, spatial, and temporal domains. The MFF module utilizes parallel subnetworks architecture to gene"},"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":"2406.08771","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-13T03:03:02Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"6fdeae108ec6b45d1673ea427ea657f0d5d36a458705bbd45f7593148362398d","abstract_canon_sha256":"5c99849b22c3fea62b22c877b8a838b84d14a74448ce4c3cba4d99ebbdcb7762"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:13.458754Z","signature_b64":"BzMDZ70SEiAELws+rL/A0ZwpxYGeuVcmfhT9GmvBRvRORndeCZgqS70cSVNLnDY5jXErpNj+9wl1plDexVrKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db7c06ec293b9f08a6d077c6a55f392caddfffa2add8a0ce403005ad83dbcf53","last_reissued_at":"2026-07-05T08:32:13.458273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:13.458273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MFF-EINV2: Multi-scale Feature Fusion across Spectral-Spatial-Temporal Domains for Sound Event Localization and Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Da Mu, Haobo Yue, Zhicheng Zhang","submitted_at":"2024-06-13T03:03:02Z","abstract_excerpt":"Sound Event Localization and Detection (SELD) involves detecting and localizing sound events using multichannel sound recordings. Previously proposed Event-Independent Network V2 (EINV2) has achieved outstanding performance on SELD. However, it still faces challenges in effectively extracting features across spectral, spatial, and temporal domains. This paper proposes a three-stage network structure named Multi-scale Feature Fusion (MFF) module to fully extract multi-scale features across spectral, spatial, and temporal domains. The MFF module utilizes parallel subnetworks architecture to gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08771","kind":"arxiv","version":2},"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/2406.08771/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":"2406.08771","created_at":"2026-07-05T08:32:13.458337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08771v2","created_at":"2026-07-05T08:32:13.458337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08771","created_at":"2026-07-05T08:32:13.458337+00:00"},{"alias_kind":"pith_short_12","alias_value":"3N6AN3BJHOPQ","created_at":"2026-07-05T08:32:13.458337+00:00"},{"alias_kind":"pith_short_16","alias_value":"3N6AN3BJHOPQRJWQ","created_at":"2026-07-05T08:32:13.458337+00:00"},{"alias_kind":"pith_short_8","alias_value":"3N6AN3BJ","created_at":"2026-07-05T08:32:13.458337+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02343","citing_title":"SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2509.17247","citing_title":"DeepASA: An Object-Oriented Multi-Purpose Network for Auditory Scene Analysis","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3N6AN3BJHOPQRJWQO7DKKXZZFS","json":"https://pith.science/pith/3N6AN3BJHOPQRJWQO7DKKXZZFS.json","graph_json":"https://pith.science/api/pith-number/3N6AN3BJHOPQRJWQO7DKKXZZFS/graph.json","events_json":"https://pith.science/api/pith-number/3N6AN3BJHOPQRJWQO7DKKXZZFS/events.json","paper":"https://pith.science/paper/3N6AN3BJ"},"agent_actions":{"view_html":"https://pith.science/pith/3N6AN3BJHOPQRJWQO7DKKXZZFS","download_json":"https://pith.science/pith/3N6AN3BJHOPQRJWQO7DKKXZZFS.json","view_paper":"https://pith.science/paper/3N6AN3BJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08771&json=true","fetch_graph":"https://pith.science/api/pith-number/3N6AN3BJHOPQRJWQO7DKKXZZFS/graph.json","fetch_events":"https://pith.science/api/pith-number/3N6AN3BJHOPQRJWQO7DKKXZZFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3N6AN3BJHOPQRJWQO7DKKXZZFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3N6AN3BJHOPQRJWQO7DKKXZZFS/action/storage_attestation","attest_author":"https://pith.science/pith/3N6AN3BJHOPQRJWQO7DKKXZZFS/action/author_attestation","sign_citation":"https://pith.science/pith/3N6AN3BJHOPQRJWQO7DKKXZZFS/action/citation_signature","submit_replication":"https://pith.science/pith/3N6AN3BJHOPQRJWQO7DKKXZZFS/action/replication_record"}},"created_at":"2026-07-05T08:32:13.458337+00:00","updated_at":"2026-07-05T08:32:13.458337+00:00"}