{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MB6JBS2NC3WKCI5JON5TKRRX47","short_pith_number":"pith:MB6JBS2N","schema_version":"1.0","canonical_sha256":"607c90cb4d16eca123a9737b354637e7cb3304cd599f039fc3823a3caa3c4bac","source":{"kind":"arxiv","id":"1804.03641","version":2},"attestation_state":"computed","paper":{"title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Andrew Owens","submitted_at":"2018-04-10T17:36:50Z","abstract_excerpt":"The thud of a bouncing ball, the onset of speech as lips open -- when visual and audio events occur together, it suggests that there might be a common, underlying event that produced both signals. In this paper, we argue that the visual and audio components of a video signal should be modeled jointly using a fused multisensory representation. We propose to learn such a representation in a self-supervised way, by training a neural network to predict whether video frames and audio are temporally aligned. We use this learned representation for three applications: (a) sound source localization, i."},"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":"1804.03641","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-10T17:36:50Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"e7d7b064acc9de0ac70cea26913610c43b3f92612c0de8685186ae91b29650e0","abstract_canon_sha256":"08b213136e5d659f2b9626884a86fd77b479c88fde69477b0503f4c2eb989f7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:49.171573Z","signature_b64":"JoEZgrD/wND9WQz+qqGuFpHXE0Bu5nZASYdPVcEKP8dtAHe7sBvkZAvH873+k3gQz7PCuDP1hmGDPziKfq3yDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"607c90cb4d16eca123a9737b354637e7cb3304cd599f039fc3823a3caa3c4bac","last_reissued_at":"2026-05-18T00:03:49.171072Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:49.171072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Andrew Owens","submitted_at":"2018-04-10T17:36:50Z","abstract_excerpt":"The thud of a bouncing ball, the onset of speech as lips open -- when visual and audio events occur together, it suggests that there might be a common, underlying event that produced both signals. In this paper, we argue that the visual and audio components of a video signal should be modeled jointly using a fused multisensory representation. We propose to learn such a representation in a self-supervised way, by training a neural network to predict whether video frames and audio are temporally aligned. We use this learned representation for three applications: (a) sound source localization, i."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.03641","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":"1804.03641","created_at":"2026-05-18T00:03:49.171149+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.03641v2","created_at":"2026-05-18T00:03:49.171149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.03641","created_at":"2026-05-18T00:03:49.171149+00:00"},{"alias_kind":"pith_short_12","alias_value":"MB6JBS2NC3WK","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"MB6JBS2NC3WKCI5J","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"MB6JBS2N","created_at":"2026-05-18T12:32:37.024351+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":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MB6JBS2NC3WKCI5JON5TKRRX47","json":"https://pith.science/pith/MB6JBS2NC3WKCI5JON5TKRRX47.json","graph_json":"https://pith.science/api/pith-number/MB6JBS2NC3WKCI5JON5TKRRX47/graph.json","events_json":"https://pith.science/api/pith-number/MB6JBS2NC3WKCI5JON5TKRRX47/events.json","paper":"https://pith.science/paper/MB6JBS2N"},"agent_actions":{"view_html":"https://pith.science/pith/MB6JBS2NC3WKCI5JON5TKRRX47","download_json":"https://pith.science/pith/MB6JBS2NC3WKCI5JON5TKRRX47.json","view_paper":"https://pith.science/paper/MB6JBS2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.03641&json=true","fetch_graph":"https://pith.science/api/pith-number/MB6JBS2NC3WKCI5JON5TKRRX47/graph.json","fetch_events":"https://pith.science/api/pith-number/MB6JBS2NC3WKCI5JON5TKRRX47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MB6JBS2NC3WKCI5JON5TKRRX47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MB6JBS2NC3WKCI5JON5TKRRX47/action/storage_attestation","attest_author":"https://pith.science/pith/MB6JBS2NC3WKCI5JON5TKRRX47/action/author_attestation","sign_citation":"https://pith.science/pith/MB6JBS2NC3WKCI5JON5TKRRX47/action/citation_signature","submit_replication":"https://pith.science/pith/MB6JBS2NC3WKCI5JON5TKRRX47/action/replication_record"}},"created_at":"2026-05-18T00:03:49.171149+00:00","updated_at":"2026-05-18T00:03:49.171149+00:00"}