{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:37RO6D3FM3Q4Z4G33CKZX3AV64","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":"6fd5333b00e529a742025b2905b268355656d58bc2930ec333f85881f96307f5","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":"2017-12-18T19:52:53Z","title_canon_sha256":"7738b164e1b7b08d7b08ec142905c3360943e4cf218d138af3737c3c21afa56d"},"schema_version":"1.0","source":{"id":"1712.06651","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.06651","created_at":"2026-05-18T00:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"1712.06651v2","created_at":"2026-05-18T00:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06651","created_at":"2026-05-18T00:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"37RO6D3FM3Q4","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"37RO6D3FM3Q4Z4G3","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"37RO6D3F","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:f181e624613a61de5eba2112e107f8edf9982e681947694c8e441c99c670cb0d","target":"graph","created_at":"2026-05-18T00:09:47Z","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"},"paper":{"abstract_excerpt":"In this paper our objectives are, first, networks that can embed audio and visual inputs into a common space that is suitable for cross-modal retrieval; and second, a network that can localize the object that sounds in an image, given the audio signal. We achieve both these objectives by training from unlabelled video using only audio-visual correspondence (AVC) as the objective function. This is a form of cross-modal self-supervision from video.\n  To this end, we design new network architectures that can be trained for cross-modal retrieval and localizing the sound source in an image, by usin","authors_text":"Andrew Zisserman, Relja Arandjelovi\\'c","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":"2017-12-18T19:52:53Z","title":"Objects that Sound"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06651","kind":"arxiv","version":2},"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:bcc17d0be25983a96aba103d44f07453cd01b0157685bc3d606cc2f74bb50b78","target":"record","created_at":"2026-05-18T00:09:47Z","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":"6fd5333b00e529a742025b2905b268355656d58bc2930ec333f85881f96307f5","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":"2017-12-18T19:52:53Z","title_canon_sha256":"7738b164e1b7b08d7b08ec142905c3360943e4cf218d138af3737c3c21afa56d"},"schema_version":"1.0","source":{"id":"1712.06651","kind":"arxiv","version":2}},"canonical_sha256":"dfe2ef0f6566e1ccf0dbd8959bec15f721ef83854fbe0a7a9c21d7b92a1cacb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfe2ef0f6566e1ccf0dbd8959bec15f721ef83854fbe0a7a9c21d7b92a1cacb2","first_computed_at":"2026-05-18T00:09:47.468743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:47.468743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CWyMWBH6HUly2i+db9jxmpxceBOy5XqWbVKFY7XBsEYUulaX6i3DXgyq/Hle0MoNGfbs1wOxmy3xKohjw8FOAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:47.469494Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.06651","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcc17d0be25983a96aba103d44f07453cd01b0157685bc3d606cc2f74bb50b78","sha256:f181e624613a61de5eba2112e107f8edf9982e681947694c8e441c99c670cb0d"],"state_sha256":"8ae028fbc41d93cd7edd6d8627b3d6afd46b90dbcb83038976cc00fa39652d23"}