{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:P6VFFITUKTA2BVSYEYYKVFXOUK","short_pith_number":"pith:P6VFFITU","schema_version":"1.0","canonical_sha256":"7faa52a27454c1a0d6582630aa96eea2a2cbc094a84b94148591f0c53a2d8a8a","source":{"kind":"arxiv","id":"1705.06979","version":2},"attestation_state":"computed","paper":{"title":"End-to-End Cross-Modality Retrieval with CCA Projections and Pairwise Ranking Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andreu Vall, Filip Korzeniowski, Gerhard Widmer, Jan Schl\\\"uter, Matthias Dorfer","submitted_at":"2017-05-19T13:23:46Z","abstract_excerpt":"Cross-modality retrieval encompasses retrieval tasks where the fetched items are of a different type than the search query, e.g., retrieving pictures relevant to a given text query. The state-of-the-art approach to cross-modality retrieval relies on learning a joint embedding space of the two modalities, where items from either modality are retrieved using nearest-neighbor search. In this work, we introduce a neural network layer based on Canonical Correlation Analysis (CCA) that learns better embedding spaces by analytically computing projections that maximize correlation. In contrast to prev"},"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":"1705.06979","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-05-19T13:23:46Z","cross_cats_sorted":[],"title_canon_sha256":"5c151106b6608c0b9cd8e1eb1e8b3830eccffccb7320249766b0d9cca72ebc71","abstract_canon_sha256":"5124c443ff82deb62c2c8c1f6229119784d9adb75e3d546638505c825d22f8c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:31.833741Z","signature_b64":"vt3rgf+RYVZnmyhI3fliGH7r4nCAy2ATEC/f9l6uRRVU6sbRZnY2lWpl54MgX/7osxLaWs14aPhze+AD1zlRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7faa52a27454c1a0d6582630aa96eea2a2cbc094a84b94148591f0c53a2d8a8a","last_reissued_at":"2026-05-18T00:18:31.833391Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:31.833391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Cross-Modality Retrieval with CCA Projections and Pairwise Ranking Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andreu Vall, Filip Korzeniowski, Gerhard Widmer, Jan Schl\\\"uter, Matthias Dorfer","submitted_at":"2017-05-19T13:23:46Z","abstract_excerpt":"Cross-modality retrieval encompasses retrieval tasks where the fetched items are of a different type than the search query, e.g., retrieving pictures relevant to a given text query. The state-of-the-art approach to cross-modality retrieval relies on learning a joint embedding space of the two modalities, where items from either modality are retrieved using nearest-neighbor search. In this work, we introduce a neural network layer based on Canonical Correlation Analysis (CCA) that learns better embedding spaces by analytically computing projections that maximize correlation. In contrast to prev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.06979","kind":"arxiv","version":2},"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":"1705.06979","created_at":"2026-05-18T00:18:31.833442+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.06979v2","created_at":"2026-05-18T00:18:31.833442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.06979","created_at":"2026-05-18T00:18:31.833442+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6VFFITUKTA2","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6VFFITUKTA2BVSY","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6VFFITU","created_at":"2026-05-18T12:31:37.085036+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/P6VFFITUKTA2BVSYEYYKVFXOUK","json":"https://pith.science/pith/P6VFFITUKTA2BVSYEYYKVFXOUK.json","graph_json":"https://pith.science/api/pith-number/P6VFFITUKTA2BVSYEYYKVFXOUK/graph.json","events_json":"https://pith.science/api/pith-number/P6VFFITUKTA2BVSYEYYKVFXOUK/events.json","paper":"https://pith.science/paper/P6VFFITU"},"agent_actions":{"view_html":"https://pith.science/pith/P6VFFITUKTA2BVSYEYYKVFXOUK","download_json":"https://pith.science/pith/P6VFFITUKTA2BVSYEYYKVFXOUK.json","view_paper":"https://pith.science/paper/P6VFFITU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.06979&json=true","fetch_graph":"https://pith.science/api/pith-number/P6VFFITUKTA2BVSYEYYKVFXOUK/graph.json","fetch_events":"https://pith.science/api/pith-number/P6VFFITUKTA2BVSYEYYKVFXOUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6VFFITUKTA2BVSYEYYKVFXOUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6VFFITUKTA2BVSYEYYKVFXOUK/action/storage_attestation","attest_author":"https://pith.science/pith/P6VFFITUKTA2BVSYEYYKVFXOUK/action/author_attestation","sign_citation":"https://pith.science/pith/P6VFFITUKTA2BVSYEYYKVFXOUK/action/citation_signature","submit_replication":"https://pith.science/pith/P6VFFITUKTA2BVSYEYYKVFXOUK/action/replication_record"}},"created_at":"2026-05-18T00:18:31.833442+00:00","updated_at":"2026-05-18T00:18:31.833442+00:00"}