{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MGC6DRCXIJYPWYRTSWI2USELPO","short_pith_number":"pith:MGC6DRCX","schema_version":"1.0","canonical_sha256":"6185e1c4574270fb62339591aa488b7b801fbfc7b10b9d31d5dd802fd54904a2","source":{"kind":"arxiv","id":"1801.02200","version":1},"attestation_state":"computed","paper":{"title":"Cross-modal Embeddings for Video and Audio Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.IR","authors_text":"Amaia Salvador, Amanda Duarte, Didac Sur\\'is, Jordi Torres, Xavier Gir\\'o-i-Nieto","submitted_at":"2018-01-07T15:43:22Z","abstract_excerpt":"The increasing amount of online videos brings several opportunities for training self-supervised neural networks. The creation of large scale datasets of videos such as the YouTube-8M allows us to deal with this large amount of data in manageable way. In this work, we find new ways of exploiting this dataset by taking advantage of the multi-modal information it provides. By means of a neural network, we are able to create links between audio and visual documents, by projecting them into a common region of the feature space, obtaining joint audio-visual embeddings. These links are used to retri"},"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":"1801.02200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-01-07T15:43:22Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"43e36193c5d9c05bd07a87e63bff0bbd862037ef65f2e20ba61d5c2563177e6b","abstract_canon_sha256":"b80cdccf36cef215a4c5c5872e39e73e49842202455e0c7f1092ec72ceb19e3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:34.580805Z","signature_b64":"g0ahkyzqFUZXi8caAGqaH0oHRJSMVNGhMcHnpse27Fk0rExWS71IYGLdttLKPu8dUSjG7a3y/3+UqO6nEtbeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6185e1c4574270fb62339591aa488b7b801fbfc7b10b9d31d5dd802fd54904a2","last_reissued_at":"2026-05-18T00:26:34.580245Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:34.580245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-modal Embeddings for Video and Audio Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.IR","authors_text":"Amaia Salvador, Amanda Duarte, Didac Sur\\'is, Jordi Torres, Xavier Gir\\'o-i-Nieto","submitted_at":"2018-01-07T15:43:22Z","abstract_excerpt":"The increasing amount of online videos brings several opportunities for training self-supervised neural networks. The creation of large scale datasets of videos such as the YouTube-8M allows us to deal with this large amount of data in manageable way. In this work, we find new ways of exploiting this dataset by taking advantage of the multi-modal information it provides. By means of a neural network, we are able to create links between audio and visual documents, by projecting them into a common region of the feature space, obtaining joint audio-visual embeddings. These links are used to retri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.02200","kind":"arxiv","version":1},"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":"1801.02200","created_at":"2026-05-18T00:26:34.580344+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.02200v1","created_at":"2026-05-18T00:26:34.580344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.02200","created_at":"2026-05-18T00:26:34.580344+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGC6DRCXIJYP","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGC6DRCXIJYPWYRT","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGC6DRCX","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MGC6DRCXIJYPWYRTSWI2USELPO","json":"https://pith.science/pith/MGC6DRCXIJYPWYRTSWI2USELPO.json","graph_json":"https://pith.science/api/pith-number/MGC6DRCXIJYPWYRTSWI2USELPO/graph.json","events_json":"https://pith.science/api/pith-number/MGC6DRCXIJYPWYRTSWI2USELPO/events.json","paper":"https://pith.science/paper/MGC6DRCX"},"agent_actions":{"view_html":"https://pith.science/pith/MGC6DRCXIJYPWYRTSWI2USELPO","download_json":"https://pith.science/pith/MGC6DRCXIJYPWYRTSWI2USELPO.json","view_paper":"https://pith.science/paper/MGC6DRCX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.02200&json=true","fetch_graph":"https://pith.science/api/pith-number/MGC6DRCXIJYPWYRTSWI2USELPO/graph.json","fetch_events":"https://pith.science/api/pith-number/MGC6DRCXIJYPWYRTSWI2USELPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGC6DRCXIJYPWYRTSWI2USELPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGC6DRCXIJYPWYRTSWI2USELPO/action/storage_attestation","attest_author":"https://pith.science/pith/MGC6DRCXIJYPWYRTSWI2USELPO/action/author_attestation","sign_citation":"https://pith.science/pith/MGC6DRCXIJYPWYRTSWI2USELPO/action/citation_signature","submit_replication":"https://pith.science/pith/MGC6DRCXIJYPWYRTSWI2USELPO/action/replication_record"}},"created_at":"2026-05-18T00:26:34.580344+00:00","updated_at":"2026-05-18T00:26:34.580344+00:00"}