{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CZ7QGOXZWEYIAVBZLNSBXZNTCQ","short_pith_number":"pith:CZ7QGOXZ","schema_version":"1.0","canonical_sha256":"167f033af9b1308054395b641be5b314252d691cc47ccfcbadbf71931bff6125","source":{"kind":"arxiv","id":"1908.03744","version":1},"attestation_state":"computed","paper":{"title":"Audio-Visual Embedding for Cross-Modal MusicVideo Retrieval through Supervised Deep CCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.MM","authors_text":"Donghuo Zeng, Keizo Oyama, Yi Yu","submitted_at":"2019-08-10T12:29:05Z","abstract_excerpt":"Deep learning has successfully shown excellent performance in learning joint representations between different data modalities. Unfortunately, little research focuses on cross-modal correlation learning where temporal structures of different data modalities, such as audio and video, should be taken into account. Music video retrieval by given musical audio is a natural way to search and interact with music contents. In this work, we study cross-modal music video retrieval in terms of emotion similarity. Particularly, audio of an arbitrary length is used to retrieve a longer or full-length musi"},"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":"1908.03744","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-08-10T12:29:05Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"88e3a2801c96d8fcc6c3c10745cee904a1ebbedf191a54fa3786b722e8256f62","abstract_canon_sha256":"f6bfc335e7d0531cab9d71476e2b5a0117f92a5381a30d06f23d32a1c8b81d27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:53:17.914413Z","signature_b64":"oYiA64R8S0UCMiWAfTZHNXpHebslzdWayrh3G6fBA5io7bAa8E8cIXKVLPgm7bA+8nP5B1wvgmvvz2gBnftEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"167f033af9b1308054395b641be5b314252d691cc47ccfcbadbf71931bff6125","last_reissued_at":"2026-07-04T23:53:17.914029Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:53:17.914029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Visual Embedding for Cross-Modal MusicVideo Retrieval through Supervised Deep CCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.MM","authors_text":"Donghuo Zeng, Keizo Oyama, Yi Yu","submitted_at":"2019-08-10T12:29:05Z","abstract_excerpt":"Deep learning has successfully shown excellent performance in learning joint representations between different data modalities. Unfortunately, little research focuses on cross-modal correlation learning where temporal structures of different data modalities, such as audio and video, should be taken into account. Music video retrieval by given musical audio is a natural way to search and interact with music contents. In this work, we study cross-modal music video retrieval in terms of emotion similarity. Particularly, audio of an arbitrary length is used to retrieve a longer or full-length musi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03744","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.03744/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":"1908.03744","created_at":"2026-07-04T23:53:17.914085+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.03744v1","created_at":"2026-07-04T23:53:17.914085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03744","created_at":"2026-07-04T23:53:17.914085+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZ7QGOXZWEYI","created_at":"2026-07-04T23:53:17.914085+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZ7QGOXZWEYIAVBZ","created_at":"2026-07-04T23:53:17.914085+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZ7QGOXZ","created_at":"2026-07-04T23:53:17.914085+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/CZ7QGOXZWEYIAVBZLNSBXZNTCQ","json":"https://pith.science/pith/CZ7QGOXZWEYIAVBZLNSBXZNTCQ.json","graph_json":"https://pith.science/api/pith-number/CZ7QGOXZWEYIAVBZLNSBXZNTCQ/graph.json","events_json":"https://pith.science/api/pith-number/CZ7QGOXZWEYIAVBZLNSBXZNTCQ/events.json","paper":"https://pith.science/paper/CZ7QGOXZ"},"agent_actions":{"view_html":"https://pith.science/pith/CZ7QGOXZWEYIAVBZLNSBXZNTCQ","download_json":"https://pith.science/pith/CZ7QGOXZWEYIAVBZLNSBXZNTCQ.json","view_paper":"https://pith.science/paper/CZ7QGOXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.03744&json=true","fetch_graph":"https://pith.science/api/pith-number/CZ7QGOXZWEYIAVBZLNSBXZNTCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CZ7QGOXZWEYIAVBZLNSBXZNTCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZ7QGOXZWEYIAVBZLNSBXZNTCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZ7QGOXZWEYIAVBZLNSBXZNTCQ/action/storage_attestation","attest_author":"https://pith.science/pith/CZ7QGOXZWEYIAVBZLNSBXZNTCQ/action/author_attestation","sign_citation":"https://pith.science/pith/CZ7QGOXZWEYIAVBZLNSBXZNTCQ/action/citation_signature","submit_replication":"https://pith.science/pith/CZ7QGOXZWEYIAVBZLNSBXZNTCQ/action/replication_record"}},"created_at":"2026-07-04T23:53:17.914085+00:00","updated_at":"2026-07-04T23:53:17.914085+00:00"}