{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FTJB3HRJY7SCCRSOPAHMR5B2LO","short_pith_number":"pith:FTJB3HRJ","schema_version":"1.0","canonical_sha256":"2cd21d9e29c7e421464e780ec8f43a5b93086e44c8a40ed0c4c55cbbfd922525","source":{"kind":"arxiv","id":"2406.09272","version":3},"attestation_state":"computed","paper":{"title":"Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Ami Baid, Changan Chen, David Harwath, Kristen Grauman, Puyuan Peng, Wei-Ning Hsu, Zihui Xue","submitted_at":"2024-06-13T16:10:19Z","abstract_excerpt":"Generating realistic audio for human actions is important for many applications, such as creating sound effects for films or virtual reality games. Existing approaches implicitly assume total correspondence between the video and audio during training, yet many sounds happen off-screen and have weak to no correspondence with the visuals -- resulting in uncontrolled ambient sounds or hallucinations at test time. We propose a novel ambient-aware audio generation model, AV-LDM. We devise a novel audio-conditioning mechanism to learn to disentangle foreground action sounds from the ambient backgrou"},"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":"2406.09272","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T16:10:19Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"f29131832f3ef4d50507f247f00db52700a81526974b7b78a3fc37d256c39e81","abstract_canon_sha256":"bd996bbc583343002b4d4385a4b4aecd291ed36b25f207deecd3ac8066687818"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:32.129016Z","signature_b64":"AtJmF9fe5xvrlpVF8pNZG9+EhrnPUsuM8OOYcvIkmHAt9nb+bJq/142XX1hag8slJTu4cFsWWVwAqCWDN6tiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cd21d9e29c7e421464e780ec8f43a5b93086e44c8a40ed0c4c55cbbfd922525","last_reissued_at":"2026-07-05T08:48:32.128547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:32.128547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Ami Baid, Changan Chen, David Harwath, Kristen Grauman, Puyuan Peng, Wei-Ning Hsu, Zihui Xue","submitted_at":"2024-06-13T16:10:19Z","abstract_excerpt":"Generating realistic audio for human actions is important for many applications, such as creating sound effects for films or virtual reality games. Existing approaches implicitly assume total correspondence between the video and audio during training, yet many sounds happen off-screen and have weak to no correspondence with the visuals -- resulting in uncontrolled ambient sounds or hallucinations at test time. We propose a novel ambient-aware audio generation model, AV-LDM. We devise a novel audio-conditioning mechanism to learn to disentangle foreground action sounds from the ambient backgrou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09272","kind":"arxiv","version":3},"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/2406.09272/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":"2406.09272","created_at":"2026-07-05T08:48:32.128604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09272v3","created_at":"2026-07-05T08:48:32.128604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09272","created_at":"2026-07-05T08:48:32.128604+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTJB3HRJY7SC","created_at":"2026-07-05T08:48:32.128604+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTJB3HRJY7SCCRSO","created_at":"2026-07-05T08:48:32.128604+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTJB3HRJ","created_at":"2026-07-05T08:48:32.128604+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/FTJB3HRJY7SCCRSOPAHMR5B2LO","json":"https://pith.science/pith/FTJB3HRJY7SCCRSOPAHMR5B2LO.json","graph_json":"https://pith.science/api/pith-number/FTJB3HRJY7SCCRSOPAHMR5B2LO/graph.json","events_json":"https://pith.science/api/pith-number/FTJB3HRJY7SCCRSOPAHMR5B2LO/events.json","paper":"https://pith.science/paper/FTJB3HRJ"},"agent_actions":{"view_html":"https://pith.science/pith/FTJB3HRJY7SCCRSOPAHMR5B2LO","download_json":"https://pith.science/pith/FTJB3HRJY7SCCRSOPAHMR5B2LO.json","view_paper":"https://pith.science/paper/FTJB3HRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09272&json=true","fetch_graph":"https://pith.science/api/pith-number/FTJB3HRJY7SCCRSOPAHMR5B2LO/graph.json","fetch_events":"https://pith.science/api/pith-number/FTJB3HRJY7SCCRSOPAHMR5B2LO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTJB3HRJY7SCCRSOPAHMR5B2LO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTJB3HRJY7SCCRSOPAHMR5B2LO/action/storage_attestation","attest_author":"https://pith.science/pith/FTJB3HRJY7SCCRSOPAHMR5B2LO/action/author_attestation","sign_citation":"https://pith.science/pith/FTJB3HRJY7SCCRSOPAHMR5B2LO/action/citation_signature","submit_replication":"https://pith.science/pith/FTJB3HRJY7SCCRSOPAHMR5B2LO/action/replication_record"}},"created_at":"2026-07-05T08:48:32.128604+00:00","updated_at":"2026-07-05T08:48:32.128604+00:00"}