{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:K47RJUHHYEA5QZOUOOSQ6CMJN6","short_pith_number":"pith:K47RJUHH","schema_version":"1.0","canonical_sha256":"573f14d0e7c101d865d473a50f09896fb5082fbf51d26bdcc5bc87963a4fab98","source":{"kind":"arxiv","id":"1701.00599","version":2},"attestation_state":"computed","paper":{"title":"AENet: Learning Deep Audio Features for Video Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"cs.MM","authors_text":"Luc Van Gool, Michael Gygli, Naoya Takahashi","submitted_at":"2017-01-03T07:35:54Z","abstract_excerpt":"We propose a new deep network for audio event recognition, called AENet. In contrast to speech, sounds coming from audio events may be produced by a wide variety of sources. Furthermore, distinguishing them often requires analyzing an extended time period due to the lack of clear sub-word units that are present in speech. In order to incorporate this long-time frequency structure of audio events, we introduce a convolutional neural network (CNN) operating on a large temporal input. In contrast to previous works this allows us to train an audio event detection system end-to-end. The combination"},"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":"1701.00599","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2017-01-03T07:35:54Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"b2f23b36c229ebe8d9782cb364080745bf2db6ca1851288ca28d28ca0bf81d9b","abstract_canon_sha256":"646c840b01be3be872346345e9da0720d723e15d2396a39bf33edc9fe8d79ffd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:23.862446Z","signature_b64":"SwHlIp8ustq0wOKNKpkvGWSrWH2Ck6IOjQSoRpQjUYjXtx5eka9lvz5axHDAZcfNelyLxys70XsXtJSo/tkHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"573f14d0e7c101d865d473a50f09896fb5082fbf51d26bdcc5bc87963a4fab98","last_reissued_at":"2026-05-18T00:53:23.861809Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:23.861809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AENet: Learning Deep Audio Features for Video Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"cs.MM","authors_text":"Luc Van Gool, Michael Gygli, Naoya Takahashi","submitted_at":"2017-01-03T07:35:54Z","abstract_excerpt":"We propose a new deep network for audio event recognition, called AENet. In contrast to speech, sounds coming from audio events may be produced by a wide variety of sources. Furthermore, distinguishing them often requires analyzing an extended time period due to the lack of clear sub-word units that are present in speech. In order to incorporate this long-time frequency structure of audio events, we introduce a convolutional neural network (CNN) operating on a large temporal input. In contrast to previous works this allows us to train an audio event detection system end-to-end. The combination"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.00599","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":"1701.00599","created_at":"2026-05-18T00:53:23.861903+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.00599v2","created_at":"2026-05-18T00:53:23.861903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.00599","created_at":"2026-05-18T00:53:23.861903+00:00"},{"alias_kind":"pith_short_12","alias_value":"K47RJUHHYEA5","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"K47RJUHHYEA5QZOU","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"K47RJUHH","created_at":"2026-05-18T12:31:24.725408+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/K47RJUHHYEA5QZOUOOSQ6CMJN6","json":"https://pith.science/pith/K47RJUHHYEA5QZOUOOSQ6CMJN6.json","graph_json":"https://pith.science/api/pith-number/K47RJUHHYEA5QZOUOOSQ6CMJN6/graph.json","events_json":"https://pith.science/api/pith-number/K47RJUHHYEA5QZOUOOSQ6CMJN6/events.json","paper":"https://pith.science/paper/K47RJUHH"},"agent_actions":{"view_html":"https://pith.science/pith/K47RJUHHYEA5QZOUOOSQ6CMJN6","download_json":"https://pith.science/pith/K47RJUHHYEA5QZOUOOSQ6CMJN6.json","view_paper":"https://pith.science/paper/K47RJUHH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.00599&json=true","fetch_graph":"https://pith.science/api/pith-number/K47RJUHHYEA5QZOUOOSQ6CMJN6/graph.json","fetch_events":"https://pith.science/api/pith-number/K47RJUHHYEA5QZOUOOSQ6CMJN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K47RJUHHYEA5QZOUOOSQ6CMJN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K47RJUHHYEA5QZOUOOSQ6CMJN6/action/storage_attestation","attest_author":"https://pith.science/pith/K47RJUHHYEA5QZOUOOSQ6CMJN6/action/author_attestation","sign_citation":"https://pith.science/pith/K47RJUHHYEA5QZOUOOSQ6CMJN6/action/citation_signature","submit_replication":"https://pith.science/pith/K47RJUHHYEA5QZOUOOSQ6CMJN6/action/replication_record"}},"created_at":"2026-05-18T00:53:23.861903+00:00","updated_at":"2026-05-18T00:53:23.861903+00:00"}