{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:STC2THKZHPUQQ5EMZX62TSTWN7","short_pith_number":"pith:STC2THKZ","schema_version":"1.0","canonical_sha256":"94c5a99d593be908748ccdfda9ca766fe61aeabd6d5c66177a1f3c56c6311faa","source":{"kind":"arxiv","id":"2409.00486","version":1},"attestation_state":"computed","paper":{"title":"Multi-scale Multi-instance Visual Sound Localization and Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Haofan Wang, Shentong Mo","submitted_at":"2024-08-31T15:43:22Z","abstract_excerpt":"Visual sound localization is a typical and challenging problem that predicts the location of objects corresponding to the sound source in a video. Previous methods mainly used the audio-visual association between global audio and one-scale visual features to localize sounding objects in each image. Despite their promising performance, they omitted multi-scale visual features of the corresponding image, and they cannot learn discriminative regions compared to ground truths. To address this issue, we propose a novel multi-scale multi-instance visual sound localization framework, namely M2VSL, th"},"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":"2409.00486","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-31T15:43:22Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"efd8326c7b6e4155299ede33cdb9d19565a2694ac5fb1e44690c45c89d6be298","abstract_canon_sha256":"50f673169ccd5c64f8298c4fd667e7c97567d4b5b394f4c64e63d5caea91477f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:48.174920Z","signature_b64":"0GkmJWv5VwVGhfMwpunnI9LNsPbz9/LfzPkXHLptWkzxaqDW5xpzDM/LND95QHChYhPVWhsB7yRP4nNfuN77Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94c5a99d593be908748ccdfda9ca766fe61aeabd6d5c66177a1f3c56c6311faa","last_reissued_at":"2026-07-05T09:01:48.174518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:48.174518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-scale Multi-instance Visual Sound Localization and Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Haofan Wang, Shentong Mo","submitted_at":"2024-08-31T15:43:22Z","abstract_excerpt":"Visual sound localization is a typical and challenging problem that predicts the location of objects corresponding to the sound source in a video. Previous methods mainly used the audio-visual association between global audio and one-scale visual features to localize sounding objects in each image. Despite their promising performance, they omitted multi-scale visual features of the corresponding image, and they cannot learn discriminative regions compared to ground truths. To address this issue, we propose a novel multi-scale multi-instance visual sound localization framework, namely M2VSL, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00486","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/2409.00486/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":"2409.00486","created_at":"2026-07-05T09:01:48.174575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00486v1","created_at":"2026-07-05T09:01:48.174575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00486","created_at":"2026-07-05T09:01:48.174575+00:00"},{"alias_kind":"pith_short_12","alias_value":"STC2THKZHPUQ","created_at":"2026-07-05T09:01:48.174575+00:00"},{"alias_kind":"pith_short_16","alias_value":"STC2THKZHPUQQ5EM","created_at":"2026-07-05T09:01:48.174575+00:00"},{"alias_kind":"pith_short_8","alias_value":"STC2THKZ","created_at":"2026-07-05T09:01:48.174575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05816","citing_title":"Whence the Voice? Self-supervised Dual-source Audio-Visual Localisation via Selective Convergence","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STC2THKZHPUQQ5EMZX62TSTWN7","json":"https://pith.science/pith/STC2THKZHPUQQ5EMZX62TSTWN7.json","graph_json":"https://pith.science/api/pith-number/STC2THKZHPUQQ5EMZX62TSTWN7/graph.json","events_json":"https://pith.science/api/pith-number/STC2THKZHPUQQ5EMZX62TSTWN7/events.json","paper":"https://pith.science/paper/STC2THKZ"},"agent_actions":{"view_html":"https://pith.science/pith/STC2THKZHPUQQ5EMZX62TSTWN7","download_json":"https://pith.science/pith/STC2THKZHPUQQ5EMZX62TSTWN7.json","view_paper":"https://pith.science/paper/STC2THKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00486&json=true","fetch_graph":"https://pith.science/api/pith-number/STC2THKZHPUQQ5EMZX62TSTWN7/graph.json","fetch_events":"https://pith.science/api/pith-number/STC2THKZHPUQQ5EMZX62TSTWN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STC2THKZHPUQQ5EMZX62TSTWN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STC2THKZHPUQQ5EMZX62TSTWN7/action/storage_attestation","attest_author":"https://pith.science/pith/STC2THKZHPUQQ5EMZX62TSTWN7/action/author_attestation","sign_citation":"https://pith.science/pith/STC2THKZHPUQQ5EMZX62TSTWN7/action/citation_signature","submit_replication":"https://pith.science/pith/STC2THKZHPUQQ5EMZX62TSTWN7/action/replication_record"}},"created_at":"2026-07-05T09:01:48.174575+00:00","updated_at":"2026-07-05T09:01:48.174575+00:00"}