{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:STC2THKZHPUQQ5EMZX62TSTWN7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"50f673169ccd5c64f8298c4fd667e7c97567d4b5b394f4c64e63d5caea91477f","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-31T15:43:22Z","title_canon_sha256":"efd8326c7b6e4155299ede33cdb9d19565a2694ac5fb1e44690c45c89d6be298"},"schema_version":"1.0","source":{"id":"2409.00486","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.00486","created_at":"2026-07-05T09:01:48Z"},{"alias_kind":"arxiv_version","alias_value":"2409.00486v1","created_at":"2026-07-05T09:01:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00486","created_at":"2026-07-05T09:01:48Z"},{"alias_kind":"pith_short_12","alias_value":"STC2THKZHPUQ","created_at":"2026-07-05T09:01:48Z"},{"alias_kind":"pith_short_16","alias_value":"STC2THKZHPUQQ5EM","created_at":"2026-07-05T09:01:48Z"},{"alias_kind":"pith_short_8","alias_value":"STC2THKZ","created_at":"2026-07-05T09:01:48Z"}],"graph_snapshots":[{"event_id":"sha256:b2b437b307db982d9f1914b8addc403bee4fa25fbf7b7f48d2a8f5d9d49e6d23","target":"graph","created_at":"2026-07-05T09:01:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.00486/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haofan Wang, Shentong Mo","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-31T15:43:22Z","title":"Multi-scale Multi-instance Visual Sound Localization and Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00486","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:019903be765b807ba350dbdac40e1bba3f8f7584c053893e2814c25bfd27e53e","target":"record","created_at":"2026-07-05T09:01:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"50f673169ccd5c64f8298c4fd667e7c97567d4b5b394f4c64e63d5caea91477f","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-31T15:43:22Z","title_canon_sha256":"efd8326c7b6e4155299ede33cdb9d19565a2694ac5fb1e44690c45c89d6be298"},"schema_version":"1.0","source":{"id":"2409.00486","kind":"arxiv","version":1}},"canonical_sha256":"94c5a99d593be908748ccdfda9ca766fe61aeabd6d5c66177a1f3c56c6311faa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94c5a99d593be908748ccdfda9ca766fe61aeabd6d5c66177a1f3c56c6311faa","first_computed_at":"2026-07-05T09:01:48.174518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:01:48.174518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0GkmJWv5VwVGhfMwpunnI9LNsPbz9/LfzPkXHLptWkzxaqDW5xpzDM/LND95QHChYhPVWhsB7yRP4nNfuN77Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:01:48.174920Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.00486","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:019903be765b807ba350dbdac40e1bba3f8f7584c053893e2814c25bfd27e53e","sha256:b2b437b307db982d9f1914b8addc403bee4fa25fbf7b7f48d2a8f5d9d49e6d23"],"state_sha256":"7840bd34cc2b162c506c6c9cb0a81a65f77825322f64a69a247234f5c208b0d2"}