{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7W3LTFFRSAMSMQUAX5HL7VU2BH","short_pith_number":"pith:7W3LTFFR","schema_version":"1.0","canonical_sha256":"fdb6b994b19019264280bf4ebfd69a09f4fdbb2b4304afb1e33b5ca6588f03bd","source":{"kind":"arxiv","id":"2407.05551","version":2},"attestation_state":"computed","paper":{"title":"Read, Watch and Scream! Sound Generation from Text and Video","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Jiyoung Lee, Sanghyuk Chun, Yujin Jeong, Yunji Kim","submitted_at":"2024-07-08T01:59:17Z","abstract_excerpt":"Despite the impressive progress of multimodal generative models, video-to-audio generation still suffers from limited performance and limits the flexibility to prioritize sound synthesis for specific objects within the scene. Conversely, text-to-audio generation methods generate high-quality audio but pose challenges in ensuring comprehensive scene depiction and time-varying control. To tackle these challenges, we propose a novel video-and-text-to-audio generation method, called \\ours, where video serves as a conditional control for a text-to-audio generation model. Especially, our method esti"},"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":"2407.05551","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T01:59:17Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"2bebe7f6f4a6bef39fd52263b9dee3edd7afcaeed4d1849b57acf7383e0549f2","abstract_canon_sha256":"2cabde5918d68eee03364392655bebe08eae4cbcd2f14357d4f48a09b359daea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:27.516382Z","signature_b64":"2Sne82YnuwNzKmsKBn+WpL5uY5Rrklmeo7rUE6Pm7aMJMvBUWXnMAL0aUuuWDZcgJ7kU3byL+8zXTWvJxwFxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdb6b994b19019264280bf4ebfd69a09f4fdbb2b4304afb1e33b5ca6588f03bd","last_reissued_at":"2026-07-05T09:54:27.515748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:27.515748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Read, Watch and Scream! Sound Generation from Text and Video","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Jiyoung Lee, Sanghyuk Chun, Yujin Jeong, Yunji Kim","submitted_at":"2024-07-08T01:59:17Z","abstract_excerpt":"Despite the impressive progress of multimodal generative models, video-to-audio generation still suffers from limited performance and limits the flexibility to prioritize sound synthesis for specific objects within the scene. Conversely, text-to-audio generation methods generate high-quality audio but pose challenges in ensuring comprehensive scene depiction and time-varying control. To tackle these challenges, we propose a novel video-and-text-to-audio generation method, called \\ours, where video serves as a conditional control for a text-to-audio generation model. Especially, our method esti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05551","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/2407.05551/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":"2407.05551","created_at":"2026-07-05T09:54:27.515838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05551v2","created_at":"2026-07-05T09:54:27.515838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05551","created_at":"2026-07-05T09:54:27.515838+00:00"},{"alias_kind":"pith_short_12","alias_value":"7W3LTFFRSAMS","created_at":"2026-07-05T09:54:27.515838+00:00"},{"alias_kind":"pith_short_16","alias_value":"7W3LTFFRSAMSMQUA","created_at":"2026-07-05T09:54:27.515838+00:00"},{"alias_kind":"pith_short_8","alias_value":"7W3LTFFR","created_at":"2026-07-05T09:54:27.515838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.23727","citing_title":"AudioMoG: Guiding Audio Generation with Mixture-of-Guidance","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2510.09065","citing_title":"MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7W3LTFFRSAMSMQUAX5HL7VU2BH","json":"https://pith.science/pith/7W3LTFFRSAMSMQUAX5HL7VU2BH.json","graph_json":"https://pith.science/api/pith-number/7W3LTFFRSAMSMQUAX5HL7VU2BH/graph.json","events_json":"https://pith.science/api/pith-number/7W3LTFFRSAMSMQUAX5HL7VU2BH/events.json","paper":"https://pith.science/paper/7W3LTFFR"},"agent_actions":{"view_html":"https://pith.science/pith/7W3LTFFRSAMSMQUAX5HL7VU2BH","download_json":"https://pith.science/pith/7W3LTFFRSAMSMQUAX5HL7VU2BH.json","view_paper":"https://pith.science/paper/7W3LTFFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05551&json=true","fetch_graph":"https://pith.science/api/pith-number/7W3LTFFRSAMSMQUAX5HL7VU2BH/graph.json","fetch_events":"https://pith.science/api/pith-number/7W3LTFFRSAMSMQUAX5HL7VU2BH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7W3LTFFRSAMSMQUAX5HL7VU2BH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7W3LTFFRSAMSMQUAX5HL7VU2BH/action/storage_attestation","attest_author":"https://pith.science/pith/7W3LTFFRSAMSMQUAX5HL7VU2BH/action/author_attestation","sign_citation":"https://pith.science/pith/7W3LTFFRSAMSMQUAX5HL7VU2BH/action/citation_signature","submit_replication":"https://pith.science/pith/7W3LTFFRSAMSMQUAX5HL7VU2BH/action/replication_record"}},"created_at":"2026-07-05T09:54:27.515838+00:00","updated_at":"2026-07-05T09:54:27.515838+00:00"}