{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LKFSZVF5YN3PUWPAE3D2TWXW5G","short_pith_number":"pith:LKFSZVF5","schema_version":"1.0","canonical_sha256":"5a8b2cd4bdc376fa59e026c7a9daf6e9b0bc8872a229785a5b15790bb93badd7","source":{"kind":"arxiv","id":"2211.10539","version":2},"attestation_state":"computed","paper":{"title":"Impact of visual assistance for automated audio captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hugo Van hamme, Wim Boes","submitted_at":"2022-11-18T23:55:13Z","abstract_excerpt":"We study the impact of visual assistance for automated audio captioning. Utilizing multi-encoder transformer architectures, which have previously been employed to introduce vision-related information in the context of sound event detection, we analyze the usefulness of incorporating a variety of pretrained features.\n  We perform experiments on a YouTube-based audiovisual data set and investigate the effect of applying the considered transfer learning technique in terms of a variety of captioning metrics.\n  We find that only one of the considered kinds of pretrained features provides consistent"},"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":"2211.10539","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-18T23:55:13Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"81bf92e32200a696b16ad41617b9bd801a482bfbe6b36f2d9a4771572a679861","abstract_canon_sha256":"4d509eb96d86ff5bfec5db38cc2b94065e31b1bcbe717f46d432ff8bf934e2bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:35.628075Z","signature_b64":"jS0cOp7ItT4g0dSkmfLyVxH8zDy9MJpBZfmzdvnPJSj/A9ZSKXBMmfrLfmu1Y34N395AlJVC67fZekMzLylADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a8b2cd4bdc376fa59e026c7a9daf6e9b0bc8872a229785a5b15790bb93badd7","last_reissued_at":"2026-07-05T05:43:35.627703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:35.627703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Impact of visual assistance for automated audio captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hugo Van hamme, Wim Boes","submitted_at":"2022-11-18T23:55:13Z","abstract_excerpt":"We study the impact of visual assistance for automated audio captioning. Utilizing multi-encoder transformer architectures, which have previously been employed to introduce vision-related information in the context of sound event detection, we analyze the usefulness of incorporating a variety of pretrained features.\n  We perform experiments on a YouTube-based audiovisual data set and investigate the effect of applying the considered transfer learning technique in terms of a variety of captioning metrics.\n  We find that only one of the considered kinds of pretrained features provides consistent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.10539","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/2211.10539/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":"2211.10539","created_at":"2026-07-05T05:43:35.627767+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.10539v2","created_at":"2026-07-05T05:43:35.627767+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.10539","created_at":"2026-07-05T05:43:35.627767+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKFSZVF5YN3P","created_at":"2026-07-05T05:43:35.627767+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKFSZVF5YN3PUWPA","created_at":"2026-07-05T05:43:35.627767+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKFSZVF5","created_at":"2026-07-05T05:43:35.627767+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/LKFSZVF5YN3PUWPAE3D2TWXW5G","json":"https://pith.science/pith/LKFSZVF5YN3PUWPAE3D2TWXW5G.json","graph_json":"https://pith.science/api/pith-number/LKFSZVF5YN3PUWPAE3D2TWXW5G/graph.json","events_json":"https://pith.science/api/pith-number/LKFSZVF5YN3PUWPAE3D2TWXW5G/events.json","paper":"https://pith.science/paper/LKFSZVF5"},"agent_actions":{"view_html":"https://pith.science/pith/LKFSZVF5YN3PUWPAE3D2TWXW5G","download_json":"https://pith.science/pith/LKFSZVF5YN3PUWPAE3D2TWXW5G.json","view_paper":"https://pith.science/paper/LKFSZVF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.10539&json=true","fetch_graph":"https://pith.science/api/pith-number/LKFSZVF5YN3PUWPAE3D2TWXW5G/graph.json","fetch_events":"https://pith.science/api/pith-number/LKFSZVF5YN3PUWPAE3D2TWXW5G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKFSZVF5YN3PUWPAE3D2TWXW5G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKFSZVF5YN3PUWPAE3D2TWXW5G/action/storage_attestation","attest_author":"https://pith.science/pith/LKFSZVF5YN3PUWPAE3D2TWXW5G/action/author_attestation","sign_citation":"https://pith.science/pith/LKFSZVF5YN3PUWPAE3D2TWXW5G/action/citation_signature","submit_replication":"https://pith.science/pith/LKFSZVF5YN3PUWPAE3D2TWXW5G/action/replication_record"}},"created_at":"2026-07-05T05:43:35.627767+00:00","updated_at":"2026-07-05T05:43:35.627767+00:00"}