{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IJX3QLIZJN7S6XA627UTJEZJRC","short_pith_number":"pith:IJX3QLIZ","schema_version":"1.0","canonical_sha256":"426fb82d194b7f2f5c1ed7e9349329889ae3ac41ee06d2c5443f229e6e07b04d","source":{"kind":"arxiv","id":"1704.02116","version":4},"attestation_state":"computed","paper":{"title":"CCL: Cross-modal Correlation Learning with Multi-grained Fusion by Hierarchical Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Jinwei Qi, Xin Huang, Yuxin Peng, Yuxin Yuan","submitted_at":"2017-04-07T07:36:00Z","abstract_excerpt":"Cross-modal retrieval has become a highlighted research topic for retrieval across multimedia data such as image and text. A two-stage learning framework is widely adopted by most existing methods based on Deep Neural Network (DNN): The first learning stage is to generate separate representation for each modality, and the second learning stage is to get the cross-modal common representation. However, the existing methods have three limitations: (1) In the first learning stage, they only model intra-modality correlation, but ignore inter-modality correlation with rich complementary context. (2)"},"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":"1704.02116","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2017-04-07T07:36:00Z","cross_cats_sorted":[],"title_canon_sha256":"1dc377bf5f7f83aebd1c5e073612308ea1854a0ec5aed2510c5b645871767a2c","abstract_canon_sha256":"763d98ac38a33cadea4d44c841f1f229fd3a34c16855fcbf988ec83dfd0a671b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:27.794505Z","signature_b64":"jbWBzCtoPRoq6HFjhY4mdWJ8Aqu9qSmmOEiuTb6OpfTPVgAfVyQqxbd3X1FSSnLcjUQk57US5bhm8mu7SoULCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"426fb82d194b7f2f5c1ed7e9349329889ae3ac41ee06d2c5443f229e6e07b04d","last_reissued_at":"2026-05-18T00:38:27.793912Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:27.793912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CCL: Cross-modal Correlation Learning with Multi-grained Fusion by Hierarchical Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Jinwei Qi, Xin Huang, Yuxin Peng, Yuxin Yuan","submitted_at":"2017-04-07T07:36:00Z","abstract_excerpt":"Cross-modal retrieval has become a highlighted research topic for retrieval across multimedia data such as image and text. A two-stage learning framework is widely adopted by most existing methods based on Deep Neural Network (DNN): The first learning stage is to generate separate representation for each modality, and the second learning stage is to get the cross-modal common representation. However, the existing methods have three limitations: (1) In the first learning stage, they only model intra-modality correlation, but ignore inter-modality correlation with rich complementary context. (2)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.02116","kind":"arxiv","version":4},"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":"1704.02116","created_at":"2026-05-18T00:38:27.794001+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.02116v4","created_at":"2026-05-18T00:38:27.794001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.02116","created_at":"2026-05-18T00:38:27.794001+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJX3QLIZJN7S","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJX3QLIZJN7S6XA6","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJX3QLIZ","created_at":"2026-05-18T12:31:21.493067+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/IJX3QLIZJN7S6XA627UTJEZJRC","json":"https://pith.science/pith/IJX3QLIZJN7S6XA627UTJEZJRC.json","graph_json":"https://pith.science/api/pith-number/IJX3QLIZJN7S6XA627UTJEZJRC/graph.json","events_json":"https://pith.science/api/pith-number/IJX3QLIZJN7S6XA627UTJEZJRC/events.json","paper":"https://pith.science/paper/IJX3QLIZ"},"agent_actions":{"view_html":"https://pith.science/pith/IJX3QLIZJN7S6XA627UTJEZJRC","download_json":"https://pith.science/pith/IJX3QLIZJN7S6XA627UTJEZJRC.json","view_paper":"https://pith.science/paper/IJX3QLIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.02116&json=true","fetch_graph":"https://pith.science/api/pith-number/IJX3QLIZJN7S6XA627UTJEZJRC/graph.json","fetch_events":"https://pith.science/api/pith-number/IJX3QLIZJN7S6XA627UTJEZJRC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJX3QLIZJN7S6XA627UTJEZJRC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJX3QLIZJN7S6XA627UTJEZJRC/action/storage_attestation","attest_author":"https://pith.science/pith/IJX3QLIZJN7S6XA627UTJEZJRC/action/author_attestation","sign_citation":"https://pith.science/pith/IJX3QLIZJN7S6XA627UTJEZJRC/action/citation_signature","submit_replication":"https://pith.science/pith/IJX3QLIZJN7S6XA627UTJEZJRC/action/replication_record"}},"created_at":"2026-05-18T00:38:27.794001+00:00","updated_at":"2026-05-18T00:38:27.794001+00:00"}