{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:I7NNA7FH5FLGNVP5VAG6KPK2LD","short_pith_number":"pith:I7NNA7FH","schema_version":"1.0","canonical_sha256":"47dad07ca7e95666d5fda80de53d5a58db2232a159780cb122a8f9db8d28973f","source":{"kind":"arxiv","id":"2211.03019","version":1},"attestation_state":"computed","paper":{"title":"Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bhavin Jawade, Deen Dayal Mohan, Dennis Fedorishin, Srirangaraj Setlur, Venu Govindaraju","submitted_at":"2022-11-06T03:48:45Z","abstract_excerpt":"Learning to localize the sound source in videos without explicit annotations is a novel area of audio-visual research. Existing work in this area focuses on creating attention maps to capture the correlation between the two modalities to localize the source of the sound. In a video, oftentimes, the objects exhibiting movement are the ones generating the sound. In this work, we capture this characteristic by modeling the optical flow in a video as a prior to better aid in localizing the sound source. We further demonstrate that the addition of flow-based attention substantially improves visual "},"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":"2211.03019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-06T03:48:45Z","cross_cats_sorted":[],"title_canon_sha256":"e9e3c8e965e795ede1cf589c927dc1a4361704d29ce3c18868274b2074fc49f6","abstract_canon_sha256":"9139301364d64b0e5a8911d08cbd547ef29e761725c4430c90e07717b56602ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:43.553809Z","signature_b64":"fd15XbEZeJVEmVAqIpAf0iR5XoPm7gumN2mkPE7ZU4dA/sq4+PusWcPgfaI3Rbwto12/ftQCllWz/pgJ5iwpCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47dad07ca7e95666d5fda80de53d5a58db2232a159780cb122a8f9db8d28973f","last_reissued_at":"2026-07-05T05:13:43.553305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:43.553305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bhavin Jawade, Deen Dayal Mohan, Dennis Fedorishin, Srirangaraj Setlur, Venu Govindaraju","submitted_at":"2022-11-06T03:48:45Z","abstract_excerpt":"Learning to localize the sound source in videos without explicit annotations is a novel area of audio-visual research. Existing work in this area focuses on creating attention maps to capture the correlation between the two modalities to localize the source of the sound. In a video, oftentimes, the objects exhibiting movement are the ones generating the sound. In this work, we capture this characteristic by modeling the optical flow in a video as a prior to better aid in localizing the sound source. We further demonstrate that the addition of flow-based attention substantially improves visual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.03019","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/2211.03019/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":"2211.03019","created_at":"2026-07-05T05:13:43.553396+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.03019v1","created_at":"2026-07-05T05:13:43.553396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.03019","created_at":"2026-07-05T05:13:43.553396+00:00"},{"alias_kind":"pith_short_12","alias_value":"I7NNA7FH5FLG","created_at":"2026-07-05T05:13:43.553396+00:00"},{"alias_kind":"pith_short_16","alias_value":"I7NNA7FH5FLGNVP5","created_at":"2026-07-05T05:13:43.553396+00:00"},{"alias_kind":"pith_short_8","alias_value":"I7NNA7FH","created_at":"2026-07-05T05:13:43.553396+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/I7NNA7FH5FLGNVP5VAG6KPK2LD","json":"https://pith.science/pith/I7NNA7FH5FLGNVP5VAG6KPK2LD.json","graph_json":"https://pith.science/api/pith-number/I7NNA7FH5FLGNVP5VAG6KPK2LD/graph.json","events_json":"https://pith.science/api/pith-number/I7NNA7FH5FLGNVP5VAG6KPK2LD/events.json","paper":"https://pith.science/paper/I7NNA7FH"},"agent_actions":{"view_html":"https://pith.science/pith/I7NNA7FH5FLGNVP5VAG6KPK2LD","download_json":"https://pith.science/pith/I7NNA7FH5FLGNVP5VAG6KPK2LD.json","view_paper":"https://pith.science/paper/I7NNA7FH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.03019&json=true","fetch_graph":"https://pith.science/api/pith-number/I7NNA7FH5FLGNVP5VAG6KPK2LD/graph.json","fetch_events":"https://pith.science/api/pith-number/I7NNA7FH5FLGNVP5VAG6KPK2LD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I7NNA7FH5FLGNVP5VAG6KPK2LD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I7NNA7FH5FLGNVP5VAG6KPK2LD/action/storage_attestation","attest_author":"https://pith.science/pith/I7NNA7FH5FLGNVP5VAG6KPK2LD/action/author_attestation","sign_citation":"https://pith.science/pith/I7NNA7FH5FLGNVP5VAG6KPK2LD/action/citation_signature","submit_replication":"https://pith.science/pith/I7NNA7FH5FLGNVP5VAG6KPK2LD/action/replication_record"}},"created_at":"2026-07-05T05:13:43.553396+00:00","updated_at":"2026-07-05T05:13:43.553396+00:00"}