{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GYRKPWCMVSAU2V5TYNV4MQVIM2","short_pith_number":"pith:GYRKPWCM","schema_version":"1.0","canonical_sha256":"3622a7d84cac814d57b3c36bc642a866bd5acad5ac760a4778a46376776cd20a","source":{"kind":"arxiv","id":"2407.01494","version":1},"attestation_state":"computed","paper":{"title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Kai Chen, Yanhong Zeng, Yicheng Gu, Yiming Zhang, Yuancheng Wang, Zhening Xing, Zhizheng Wu","submitted_at":"2024-07-01T17:35:56Z","abstract_excerpt":"We study Neural Foley, the automatic generation of high-quality sound effects synchronizing with videos, enabling an immersive audio-visual experience. Despite its wide range of applications, existing approaches encounter limitations when it comes to simultaneously synthesizing high-quality and video-aligned (i.e.,, semantic relevant and temporal synchronized) sounds. To overcome these limitations, we propose FoleyCrafter, a novel framework that leverages a pre-trained text-to-audio model to ensure high-quality audio generation. FoleyCrafter comprises two key components: the semantic adapter f"},"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":"2407.01494","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T17:35:56Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b31397c32be71cc81ed26d6dd6055fc5f4b03d99d4ab4fa815573c347cdbc3a4","abstract_canon_sha256":"73db4d9cd00b80b5ae5c69c59f4b9c87ffa47681db7e8370ac4a8e38c7b9d1be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:48.788678Z","signature_b64":"ghUrcz3dv7LLw0c/fUQb2R25xE67KlIsvmup6GV/LpDnhBZhuiTbgjkymF7DmE056Yyxcxb1rJzpggcLu5zSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3622a7d84cac814d57b3c36bc642a866bd5acad5ac760a4778a46376776cd20a","last_reissued_at":"2026-07-05T08:38:48.788244Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:48.788244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Kai Chen, Yanhong Zeng, Yicheng Gu, Yiming Zhang, Yuancheng Wang, Zhening Xing, Zhizheng Wu","submitted_at":"2024-07-01T17:35:56Z","abstract_excerpt":"We study Neural Foley, the automatic generation of high-quality sound effects synchronizing with videos, enabling an immersive audio-visual experience. Despite its wide range of applications, existing approaches encounter limitations when it comes to simultaneously synthesizing high-quality and video-aligned (i.e.,, semantic relevant and temporal synchronized) sounds. To overcome these limitations, we propose FoleyCrafter, a novel framework that leverages a pre-trained text-to-audio model to ensure high-quality audio generation. FoleyCrafter comprises two key components: the semantic adapter f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01494","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/2407.01494/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":"2407.01494","created_at":"2026-07-05T08:38:48.788306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01494v1","created_at":"2026-07-05T08:38:48.788306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01494","created_at":"2026-07-05T08:38:48.788306+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYRKPWCMVSAU","created_at":"2026-07-05T08:38:48.788306+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYRKPWCMVSAU2V5T","created_at":"2026-07-05T08:38:48.788306+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYRKPWCM","created_at":"2026-07-05T08:38:48.788306+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06405","citing_title":"Precise Video-to-Audio Generation with Cross-Modal Alignment in Latent Space","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12555","citing_title":"AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26244","citing_title":"LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30339","citing_title":"Benchmarking Single-Factor Physical Video-to-Audio Generation","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2510.02307","citing_title":"NoiseShift: Resolution-Aware Noise Recalibration for Better Low-Resolution Image Generation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23994","citing_title":"PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2509.18272","citing_title":"StereoFoley: Object-Aware Stereo Audio Generation from Video","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23727","citing_title":"AudioMoG: Guiding Audio Generation with Mixture-of-Guidance","ref_index":74,"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":28,"is_internal_anchor":false},{"citing_arxiv_id":"2512.00336","citing_title":"MVAD: A Benchmark Dataset for Multimodal AI-Generated Video-Audio Detection","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2512.20211","citing_title":"Aliasing-Free Neural Audio Synthesis","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23994","citing_title":"PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20981","citing_title":"Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2601.03233","citing_title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00495","citing_title":"MMAudio-LABEL: Audio Event Labeling via Audio Generation for Silent Video","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05731","citing_title":"FoleyDesigner: Immersive Stereo Foley Generation with Precise Spatio-Temporal Alignment for Film Clips","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04348","citing_title":"OmniSonic: Towards Universal and Holistic Audio Generation from Video and Text","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14707","citing_title":"Geo2Sound: A Scalable Geo-Aligned Framework for Soundscape Generation from Satellite Imagery","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYRKPWCMVSAU2V5TYNV4MQVIM2","json":"https://pith.science/pith/GYRKPWCMVSAU2V5TYNV4MQVIM2.json","graph_json":"https://pith.science/api/pith-number/GYRKPWCMVSAU2V5TYNV4MQVIM2/graph.json","events_json":"https://pith.science/api/pith-number/GYRKPWCMVSAU2V5TYNV4MQVIM2/events.json","paper":"https://pith.science/paper/GYRKPWCM"},"agent_actions":{"view_html":"https://pith.science/pith/GYRKPWCMVSAU2V5TYNV4MQVIM2","download_json":"https://pith.science/pith/GYRKPWCMVSAU2V5TYNV4MQVIM2.json","view_paper":"https://pith.science/paper/GYRKPWCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01494&json=true","fetch_graph":"https://pith.science/api/pith-number/GYRKPWCMVSAU2V5TYNV4MQVIM2/graph.json","fetch_events":"https://pith.science/api/pith-number/GYRKPWCMVSAU2V5TYNV4MQVIM2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYRKPWCMVSAU2V5TYNV4MQVIM2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYRKPWCMVSAU2V5TYNV4MQVIM2/action/storage_attestation","attest_author":"https://pith.science/pith/GYRKPWCMVSAU2V5TYNV4MQVIM2/action/author_attestation","sign_citation":"https://pith.science/pith/GYRKPWCMVSAU2V5TYNV4MQVIM2/action/citation_signature","submit_replication":"https://pith.science/pith/GYRKPWCMVSAU2V5TYNV4MQVIM2/action/replication_record"}},"created_at":"2026-07-05T08:38:48.788306+00:00","updated_at":"2026-07-05T08:38:48.788306+00:00"}