{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SCQGL5Z6RGLEII5VTGN5FRRY7S","short_pith_number":"pith:SCQGL5Z6","schema_version":"1.0","canonical_sha256":"90a065f73e89964423b5999bd2c638fc8930b6eb659ab8263daec34615d839db","source":{"kind":"arxiv","id":"2004.12943","version":3},"attestation_state":"computed","paper":{"title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ishan Misra, Nuno Vasconcelos, Pedro Morgado","submitted_at":"2020-04-27T16:59:49Z","abstract_excerpt":"We present a self-supervised learning approach to learn audio-visual representations from video and audio. Our method uses contrastive learning for cross-modal discrimination of video from audio and vice-versa. We show that optimizing for cross-modal discrimination, rather than within-modal discrimination, is important to learn good representations from video and audio. With this simple but powerful insight, our method achieves highly competitive performance when finetuned on action recognition tasks. Furthermore, while recent work in contrastive learning defines positive and negative samples "},"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":"2004.12943","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-27T16:59:49Z","cross_cats_sorted":[],"title_canon_sha256":"485dc231b1185ab8364eebac59260205becf722008405196633a6c42e078fae9","abstract_canon_sha256":"d801e9fa43b274615fa371ad1abf7f2c9ca601d9bcc38bc7193f8d193f33129b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:10.423369Z","signature_b64":"/CJgPeQSn04/dLRZIzOnUuVycj1eXrpdfpsbeaJvzruOPAeYcA6TltZb59b/neftYKTjFLt0jALr6C1ERj5gDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90a065f73e89964423b5999bd2c638fc8930b6eb659ab8263daec34615d839db","last_reissued_at":"2026-07-05T02:27:10.422901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:10.422901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ishan Misra, Nuno Vasconcelos, Pedro Morgado","submitted_at":"2020-04-27T16:59:49Z","abstract_excerpt":"We present a self-supervised learning approach to learn audio-visual representations from video and audio. Our method uses contrastive learning for cross-modal discrimination of video from audio and vice-versa. We show that optimizing for cross-modal discrimination, rather than within-modal discrimination, is important to learn good representations from video and audio. With this simple but powerful insight, our method achieves highly competitive performance when finetuned on action recognition tasks. Furthermore, while recent work in contrastive learning defines positive and negative samples "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12943","kind":"arxiv","version":3},"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/2004.12943/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":"2004.12943","created_at":"2026-07-05T02:27:10.422960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.12943v3","created_at":"2026-07-05T02:27:10.422960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12943","created_at":"2026-07-05T02:27:10.422960+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCQGL5Z6RGLE","created_at":"2026-07-05T02:27:10.422960+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCQGL5Z6RGLEII5V","created_at":"2026-07-05T02:27:10.422960+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCQGL5Z6","created_at":"2026-07-05T02:27:10.422960+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.14427","citing_title":"Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SCQGL5Z6RGLEII5VTGN5FRRY7S","json":"https://pith.science/pith/SCQGL5Z6RGLEII5VTGN5FRRY7S.json","graph_json":"https://pith.science/api/pith-number/SCQGL5Z6RGLEII5VTGN5FRRY7S/graph.json","events_json":"https://pith.science/api/pith-number/SCQGL5Z6RGLEII5VTGN5FRRY7S/events.json","paper":"https://pith.science/paper/SCQGL5Z6"},"agent_actions":{"view_html":"https://pith.science/pith/SCQGL5Z6RGLEII5VTGN5FRRY7S","download_json":"https://pith.science/pith/SCQGL5Z6RGLEII5VTGN5FRRY7S.json","view_paper":"https://pith.science/paper/SCQGL5Z6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.12943&json=true","fetch_graph":"https://pith.science/api/pith-number/SCQGL5Z6RGLEII5VTGN5FRRY7S/graph.json","fetch_events":"https://pith.science/api/pith-number/SCQGL5Z6RGLEII5VTGN5FRRY7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCQGL5Z6RGLEII5VTGN5FRRY7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCQGL5Z6RGLEII5VTGN5FRRY7S/action/storage_attestation","attest_author":"https://pith.science/pith/SCQGL5Z6RGLEII5VTGN5FRRY7S/action/author_attestation","sign_citation":"https://pith.science/pith/SCQGL5Z6RGLEII5VTGN5FRRY7S/action/citation_signature","submit_replication":"https://pith.science/pith/SCQGL5Z6RGLEII5VTGN5FRRY7S/action/replication_record"}},"created_at":"2026-07-05T02:27:10.422960+00:00","updated_at":"2026-07-05T02:27:10.422960+00:00"}