{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EQI4KFJ47AA7JM2SSF7NIOIYRH","short_pith_number":"pith:EQI4KFJ4","schema_version":"1.0","canonical_sha256":"2411c5153cf801f4b352917ed4391889e2f8cd144d03750148e245a1faecbd38","source":{"kind":"arxiv","id":"1908.03737","version":3},"attestation_state":"computed","paper":{"title":"Deep Triplet Neural Networks with Cluster-CCA for Audio-Visual Cross-modal Retrieval","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":"2019-08-10T12:03:48Z","abstract_excerpt":"Cross-modal retrieval aims to retrieve data in one modality by a query in another modality, which has been a very interesting research issue in the field of multimedia, information retrieval, and computer vision, and database. Most existing works focus on cross-modal retrieval between text-image, text-video, and lyrics-audio.Little research addresses cross-modal retrieval between audio and video due to limited audio-video paired datasets and semantic information. The main challenge of audio-visual cross-modal retrieval task focuses on learning joint embeddings from a shared subspace for comput"},"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":"1908.03737","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-08-10T12:03:48Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"eff0be5fd65dad141f31fe4a719b5c0b8228e6976afcbfaa118b185d56ce371e","abstract_canon_sha256":"064b2d053ee53b749e01146819fc6dd08e95680587aa394bdcbf8fac165eac1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:39.957148Z","signature_b64":"DyHET912L8QUb0jgCZGoYhxrC9vx3OMAJEWatpHHGFFNc0mBA1xIuypZAy9bOVQ01E3n3WLpxlfDdZucR+YGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2411c5153cf801f4b352917ed4391889e2f8cd144d03750148e245a1faecbd38","last_reissued_at":"2026-07-05T02:37:39.956701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:39.956701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Triplet Neural Networks with Cluster-CCA for Audio-Visual Cross-modal Retrieval","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":"2019-08-10T12:03:48Z","abstract_excerpt":"Cross-modal retrieval aims to retrieve data in one modality by a query in another modality, which has been a very interesting research issue in the field of multimedia, information retrieval, and computer vision, and database. Most existing works focus on cross-modal retrieval between text-image, text-video, and lyrics-audio.Little research addresses cross-modal retrieval between audio and video due to limited audio-video paired datasets and semantic information. The main challenge of audio-visual cross-modal retrieval task focuses on learning joint embeddings from a shared subspace for comput"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03737","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/1908.03737/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":"1908.03737","created_at":"2026-07-05T02:37:39.956758+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.03737v3","created_at":"2026-07-05T02:37:39.956758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03737","created_at":"2026-07-05T02:37:39.956758+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQI4KFJ47AA7","created_at":"2026-07-05T02:37:39.956758+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQI4KFJ47AA7JM2S","created_at":"2026-07-05T02:37:39.956758+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQI4KFJ4","created_at":"2026-07-05T02:37:39.956758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.07673","citing_title":"Learning Joint Embedding for Cross-Modal Retrieval","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQI4KFJ47AA7JM2SSF7NIOIYRH","json":"https://pith.science/pith/EQI4KFJ47AA7JM2SSF7NIOIYRH.json","graph_json":"https://pith.science/api/pith-number/EQI4KFJ47AA7JM2SSF7NIOIYRH/graph.json","events_json":"https://pith.science/api/pith-number/EQI4KFJ47AA7JM2SSF7NIOIYRH/events.json","paper":"https://pith.science/paper/EQI4KFJ4"},"agent_actions":{"view_html":"https://pith.science/pith/EQI4KFJ47AA7JM2SSF7NIOIYRH","download_json":"https://pith.science/pith/EQI4KFJ47AA7JM2SSF7NIOIYRH.json","view_paper":"https://pith.science/paper/EQI4KFJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.03737&json=true","fetch_graph":"https://pith.science/api/pith-number/EQI4KFJ47AA7JM2SSF7NIOIYRH/graph.json","fetch_events":"https://pith.science/api/pith-number/EQI4KFJ47AA7JM2SSF7NIOIYRH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQI4KFJ47AA7JM2SSF7NIOIYRH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQI4KFJ47AA7JM2SSF7NIOIYRH/action/storage_attestation","attest_author":"https://pith.science/pith/EQI4KFJ47AA7JM2SSF7NIOIYRH/action/author_attestation","sign_citation":"https://pith.science/pith/EQI4KFJ47AA7JM2SSF7NIOIYRH/action/citation_signature","submit_replication":"https://pith.science/pith/EQI4KFJ47AA7JM2SSF7NIOIYRH/action/replication_record"}},"created_at":"2026-07-05T02:37:39.956758+00:00","updated_at":"2026-07-05T02:37:39.956758+00:00"}