{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UUX4HMX53VR6IAEJABQ3AZHMC5","short_pith_number":"pith:UUX4HMX5","schema_version":"1.0","canonical_sha256":"a52fc3b2fddd63e400890061b064ec177e8174af9026c90e43f6027e2c696ba3","source":{"kind":"arxiv","id":"2305.18753","version":1},"attestation_state":"computed","paper":{"title":"Dual Transformer Decoder based Features Fusion Network for Automated Audio Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jianyuan Sun, Mark D. Plumbley, Volkan K{\\i}l{\\i}\\c{c}, Wenwu Wang, Xinhao Mei, Xubo Liu","submitted_at":"2023-05-30T05:28:07Z","abstract_excerpt":"Automated audio captioning (AAC) which generates textual descriptions of audio content. Existing AAC models achieve good results but only use the high-dimensional representation of the encoder. There is always insufficient information learning of high-dimensional methods owing to high-dimensional representations having a large amount of information. In this paper, a new encoder-decoder model called the Low- and High-Dimensional Feature Fusion (LHDFF) is proposed. LHDFF uses a new PANNs encoder called Residual PANNs (RPANNs) to fuse low- and high-dimensional features. Low-dimensional features c"},"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":"2305.18753","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-30T05:28:07Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"63612545fe77154f3564bf61d0d76ff1f778e4dff068a65a0b446feb4a55b60a","abstract_canon_sha256":"3e0ce9c1ebe3a2320d1f12be8888a401b7311bdae1bbb565ddddce14b182594d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:04.517607Z","signature_b64":"sXdyALx4rM3i7/Bl8Ew/+aY+bq9m88JtbxakfhuJpsPDaxHb2k4qZTQulZRtufryLMT7wta16o0OWO25ClZTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a52fc3b2fddd63e400890061b064ec177e8174af9026c90e43f6027e2c696ba3","last_reissued_at":"2026-07-05T06:15:04.517188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:04.517188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Transformer Decoder based Features Fusion Network for Automated Audio Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jianyuan Sun, Mark D. Plumbley, Volkan K{\\i}l{\\i}\\c{c}, Wenwu Wang, Xinhao Mei, Xubo Liu","submitted_at":"2023-05-30T05:28:07Z","abstract_excerpt":"Automated audio captioning (AAC) which generates textual descriptions of audio content. Existing AAC models achieve good results but only use the high-dimensional representation of the encoder. There is always insufficient information learning of high-dimensional methods owing to high-dimensional representations having a large amount of information. In this paper, a new encoder-decoder model called the Low- and High-Dimensional Feature Fusion (LHDFF) is proposed. LHDFF uses a new PANNs encoder called Residual PANNs (RPANNs) to fuse low- and high-dimensional features. Low-dimensional features c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18753","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/2305.18753/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":"2305.18753","created_at":"2026-07-05T06:15:04.517249+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18753v1","created_at":"2026-07-05T06:15:04.517249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18753","created_at":"2026-07-05T06:15:04.517249+00:00"},{"alias_kind":"pith_short_12","alias_value":"UUX4HMX53VR6","created_at":"2026-07-05T06:15:04.517249+00:00"},{"alias_kind":"pith_short_16","alias_value":"UUX4HMX53VR6IAEJ","created_at":"2026-07-05T06:15:04.517249+00:00"},{"alias_kind":"pith_short_8","alias_value":"UUX4HMX5","created_at":"2026-07-05T06:15:04.517249+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/UUX4HMX53VR6IAEJABQ3AZHMC5","json":"https://pith.science/pith/UUX4HMX53VR6IAEJABQ3AZHMC5.json","graph_json":"https://pith.science/api/pith-number/UUX4HMX53VR6IAEJABQ3AZHMC5/graph.json","events_json":"https://pith.science/api/pith-number/UUX4HMX53VR6IAEJABQ3AZHMC5/events.json","paper":"https://pith.science/paper/UUX4HMX5"},"agent_actions":{"view_html":"https://pith.science/pith/UUX4HMX53VR6IAEJABQ3AZHMC5","download_json":"https://pith.science/pith/UUX4HMX53VR6IAEJABQ3AZHMC5.json","view_paper":"https://pith.science/paper/UUX4HMX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18753&json=true","fetch_graph":"https://pith.science/api/pith-number/UUX4HMX53VR6IAEJABQ3AZHMC5/graph.json","fetch_events":"https://pith.science/api/pith-number/UUX4HMX53VR6IAEJABQ3AZHMC5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UUX4HMX53VR6IAEJABQ3AZHMC5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UUX4HMX53VR6IAEJABQ3AZHMC5/action/storage_attestation","attest_author":"https://pith.science/pith/UUX4HMX53VR6IAEJABQ3AZHMC5/action/author_attestation","sign_citation":"https://pith.science/pith/UUX4HMX53VR6IAEJABQ3AZHMC5/action/citation_signature","submit_replication":"https://pith.science/pith/UUX4HMX53VR6IAEJABQ3AZHMC5/action/replication_record"}},"created_at":"2026-07-05T06:15:04.517249+00:00","updated_at":"2026-07-05T06:15:04.517249+00:00"}