{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:37RO6D3FM3Q4Z4G33CKZX3AV64","short_pith_number":"pith:37RO6D3F","schema_version":"1.0","canonical_sha256":"dfe2ef0f6566e1ccf0dbd8959bec15f721ef83854fbe0a7a9c21d7b92a1cacb2","source":{"kind":"arxiv","id":"1712.06651","version":2},"attestation_state":"computed","paper":{"title":"Objects that Sound","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":"Andrew Zisserman, Relja Arandjelovi\\'c","submitted_at":"2017-12-18T19:52:53Z","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"},"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":"1712.06651","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T19:52:53Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"7738b164e1b7b08d7b08ec142905c3360943e4cf218d138af3737c3c21afa56d","abstract_canon_sha256":"6fd5333b00e529a742025b2905b268355656d58bc2930ec333f85881f96307f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:47.469494Z","signature_b64":"CWyMWBH6HUly2i+db9jxmpxceBOy5XqWbVKFY7XBsEYUulaX6i3DXgyq/Hle0MoNGfbs1wOxmy3xKohjw8FOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfe2ef0f6566e1ccf0dbd8959bec15f721ef83854fbe0a7a9c21d7b92a1cacb2","last_reissued_at":"2026-05-18T00:09:47.468743Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:47.468743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Objects that Sound","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":"Andrew Zisserman, Relja Arandjelovi\\'c","submitted_at":"2017-12-18T19:52:53Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06651","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1712.06651","created_at":"2026-05-18T00:09:47.468871+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.06651v2","created_at":"2026-05-18T00:09:47.468871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06651","created_at":"2026-05-18T00:09:47.468871+00:00"},{"alias_kind":"pith_short_12","alias_value":"37RO6D3FM3Q4","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"37RO6D3FM3Q4Z4G3","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"37RO6D3F","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.11879","citing_title":"Multi-task Self-Supervised Learning for Human Activity Detection","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37RO6D3FM3Q4Z4G33CKZX3AV64","json":"https://pith.science/pith/37RO6D3FM3Q4Z4G33CKZX3AV64.json","graph_json":"https://pith.science/api/pith-number/37RO6D3FM3Q4Z4G33CKZX3AV64/graph.json","events_json":"https://pith.science/api/pith-number/37RO6D3FM3Q4Z4G33CKZX3AV64/events.json","paper":"https://pith.science/paper/37RO6D3F"},"agent_actions":{"view_html":"https://pith.science/pith/37RO6D3FM3Q4Z4G33CKZX3AV64","download_json":"https://pith.science/pith/37RO6D3FM3Q4Z4G33CKZX3AV64.json","view_paper":"https://pith.science/paper/37RO6D3F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.06651&json=true","fetch_graph":"https://pith.science/api/pith-number/37RO6D3FM3Q4Z4G33CKZX3AV64/graph.json","fetch_events":"https://pith.science/api/pith-number/37RO6D3FM3Q4Z4G33CKZX3AV64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37RO6D3FM3Q4Z4G33CKZX3AV64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37RO6D3FM3Q4Z4G33CKZX3AV64/action/storage_attestation","attest_author":"https://pith.science/pith/37RO6D3FM3Q4Z4G33CKZX3AV64/action/author_attestation","sign_citation":"https://pith.science/pith/37RO6D3FM3Q4Z4G33CKZX3AV64/action/citation_signature","submit_replication":"https://pith.science/pith/37RO6D3FM3Q4Z4G33CKZX3AV64/action/replication_record"}},"created_at":"2026-05-18T00:09:47.468871+00:00","updated_at":"2026-05-18T00:09:47.468871+00:00"}