{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7UQFLTHEGH4SQFY66D2K3XC3OQ","short_pith_number":"pith:7UQFLTHE","schema_version":"1.0","canonical_sha256":"fd2055cce431f928171ef0f4addc5b743e4c1107aa2bccc007a2d0fb7a990c70","source":{"kind":"arxiv","id":"1712.09673","version":2},"attestation_state":"computed","paper":{"title":"Multiple Instance Deep Learning for Weakly Supervised Small-Footprint Audio Event Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Florian Metze, Joseph Szurley, Juncheng Li, Samarjit Das, Shao-Yen Tseng, Yun Wang","submitted_at":"2017-12-27T20:30:45Z","abstract_excerpt":"State-of-the-art audio event detection (AED) systems rely on supervised learning using strongly labeled data. However, this dependence severely limits scalability to large-scale datasets where fine resolution annotations are too expensive to obtain. In this paper, we propose a small-footprint multiple instance learning (MIL) framework for multi-class AED using weakly annotated labels. The proposed MIL framework uses audio embeddings extracted from a pre-trained convolutional neural network as input features. We show that by using audio embeddings the MIL framework can be implemented using a si"},"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":"1712.09673","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-12-27T20:30:45Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"0122200b87a980f9f93955fa1b6a3f30ce1dd0cf1762ee80f64aaba4cea70015","abstract_canon_sha256":"6ec4d38911c940c5846cee65536f3223950144b0e6a3dd9ab4a7e9a0f89b8644"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:16.250373Z","signature_b64":"hdjkuX4GKW0u84mVS1GTNmp4tk7FHfpoeIFFlw6/m8mKXn4WFD1brP3+7Db84DkM2yeCG5JS3ae5pHKQ0/acBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd2055cce431f928171ef0f4addc5b743e4c1107aa2bccc007a2d0fb7a990c70","last_reissued_at":"2026-05-18T00:20:16.249750Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:16.249750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiple Instance Deep Learning for Weakly Supervised Small-Footprint Audio Event Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Florian Metze, Joseph Szurley, Juncheng Li, Samarjit Das, Shao-Yen Tseng, Yun Wang","submitted_at":"2017-12-27T20:30:45Z","abstract_excerpt":"State-of-the-art audio event detection (AED) systems rely on supervised learning using strongly labeled data. However, this dependence severely limits scalability to large-scale datasets where fine resolution annotations are too expensive to obtain. In this paper, we propose a small-footprint multiple instance learning (MIL) framework for multi-class AED using weakly annotated labels. The proposed MIL framework uses audio embeddings extracted from a pre-trained convolutional neural network as input features. We show that by using audio embeddings the MIL framework can be implemented using a si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09673","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":""},"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":"1712.09673","created_at":"2026-05-18T00:20:16.249837+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.09673v2","created_at":"2026-05-18T00:20:16.249837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09673","created_at":"2026-05-18T00:20:16.249837+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UQFLTHEGH4S","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UQFLTHEGH4SQFY6","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UQFLTHE","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7UQFLTHEGH4SQFY66D2K3XC3OQ","json":"https://pith.science/pith/7UQFLTHEGH4SQFY66D2K3XC3OQ.json","graph_json":"https://pith.science/api/pith-number/7UQFLTHEGH4SQFY66D2K3XC3OQ/graph.json","events_json":"https://pith.science/api/pith-number/7UQFLTHEGH4SQFY66D2K3XC3OQ/events.json","paper":"https://pith.science/paper/7UQFLTHE"},"agent_actions":{"view_html":"https://pith.science/pith/7UQFLTHEGH4SQFY66D2K3XC3OQ","download_json":"https://pith.science/pith/7UQFLTHEGH4SQFY66D2K3XC3OQ.json","view_paper":"https://pith.science/paper/7UQFLTHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.09673&json=true","fetch_graph":"https://pith.science/api/pith-number/7UQFLTHEGH4SQFY66D2K3XC3OQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7UQFLTHEGH4SQFY66D2K3XC3OQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UQFLTHEGH4SQFY66D2K3XC3OQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UQFLTHEGH4SQFY66D2K3XC3OQ/action/storage_attestation","attest_author":"https://pith.science/pith/7UQFLTHEGH4SQFY66D2K3XC3OQ/action/author_attestation","sign_citation":"https://pith.science/pith/7UQFLTHEGH4SQFY66D2K3XC3OQ/action/citation_signature","submit_replication":"https://pith.science/pith/7UQFLTHEGH4SQFY66D2K3XC3OQ/action/replication_record"}},"created_at":"2026-05-18T00:20:16.249837+00:00","updated_at":"2026-05-18T00:20:16.249837+00:00"}