{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:CZ7QGOXZWEYIAVBZLNSBXZNTCQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f6bfc335e7d0531cab9d71476e2b5a0117f92a5381a30d06f23d32a1c8b81d27","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-08-10T12:29:05Z","title_canon_sha256":"88e3a2801c96d8fcc6c3c10745cee904a1ebbedf191a54fa3786b722e8256f62"},"schema_version":"1.0","source":{"id":"1908.03744","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.03744","created_at":"2026-07-04T23:53:17Z"},{"alias_kind":"arxiv_version","alias_value":"1908.03744v1","created_at":"2026-07-04T23:53:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03744","created_at":"2026-07-04T23:53:17Z"},{"alias_kind":"pith_short_12","alias_value":"CZ7QGOXZWEYI","created_at":"2026-07-04T23:53:17Z"},{"alias_kind":"pith_short_16","alias_value":"CZ7QGOXZWEYIAVBZ","created_at":"2026-07-04T23:53:17Z"},{"alias_kind":"pith_short_8","alias_value":"CZ7QGOXZ","created_at":"2026-07-04T23:53:17Z"}],"graph_snapshots":[{"event_id":"sha256:f614792683df7eca51d0705a3552f8482473d3d256dffc8fa59bf4c2fa5038f9","target":"graph","created_at":"2026-07-04T23:53:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.03744/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Donghuo Zeng, Keizo Oyama, Yi Yu","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-08-10T12:29:05Z","title":"Audio-Visual Embedding for Cross-Modal MusicVideo Retrieval through Supervised Deep CCA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03744","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d6491512bbf80942b33b61391e8990d0482909cfdae377f215c4873d32852351","target":"record","created_at":"2026-07-04T23:53:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f6bfc335e7d0531cab9d71476e2b5a0117f92a5381a30d06f23d32a1c8b81d27","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-08-10T12:29:05Z","title_canon_sha256":"88e3a2801c96d8fcc6c3c10745cee904a1ebbedf191a54fa3786b722e8256f62"},"schema_version":"1.0","source":{"id":"1908.03744","kind":"arxiv","version":1}},"canonical_sha256":"167f033af9b1308054395b641be5b314252d691cc47ccfcbadbf71931bff6125","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"167f033af9b1308054395b641be5b314252d691cc47ccfcbadbf71931bff6125","first_computed_at":"2026-07-04T23:53:17.914029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:53:17.914029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oYiA64R8S0UCMiWAfTZHNXpHebslzdWayrh3G6fBA5io7bAa8E8cIXKVLPgm7bA+8nP5B1wvgmvvz2gBnftEAg==","signature_status":"signed_v1","signed_at":"2026-07-04T23:53:17.914413Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.03744","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6491512bbf80942b33b61391e8990d0482909cfdae377f215c4873d32852351","sha256:f614792683df7eca51d0705a3552f8482473d3d256dffc8fa59bf4c2fa5038f9"],"state_sha256":"5355baa96d252da5c4e44516c12de4656f22a3ef0ab4d13d65a2ab50d3b5164b"}