{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CYAYXFETUQT65DVBNHREHVH7OM","short_pith_number":"pith:CYAYXFET","schema_version":"1.0","canonical_sha256":"16018b9493a427ee8ea169e243d4ff732f49e4c6564a1982312fa52616b111c1","source":{"kind":"arxiv","id":"1807.07364","version":1},"attestation_state":"computed","paper":{"title":"Revisiting Cross Modal Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alessandro Calefati, Ignazio Gallo, Muhammad Kamran Janjua, Shah Nawaz","submitted_at":"2018-07-19T12:35:24Z","abstract_excerpt":"This paper proposes a cross-modal retrieval system that leverages on image and text encoding. Most multimodal architectures employ separate networks for each modality to capture the semantic relationship between them. However, in our work image-text encoding can achieve comparable results in terms of cross-modal retrieval without having to use a separate network for each modality. We show that text encodings can capture semantic relationships between multiple modalities. In our knowledge, this work is the first of its kind in terms of employing a single network and fused image-text embedding f"},"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":"1807.07364","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-19T12:35:24Z","cross_cats_sorted":[],"title_canon_sha256":"37c613b76dccc62d16090e4b002785ff00e59398dad541100225f1c2d59094cf","abstract_canon_sha256":"e6d412afb3ef9f89c4204a2160df9fa33ded3cd0855dd470ea81dfa0760fe793"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:20.343310Z","signature_b64":"3dSDXgRISxHM9tHb7E7rSIuUF49XCsWzlNUFi3ar5ihuGqp+iwqCGgUGN6PvZkkscmX73WOv/CnNUydmt5tFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16018b9493a427ee8ea169e243d4ff732f49e4c6564a1982312fa52616b111c1","last_reissued_at":"2026-05-18T00:10:20.342782Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:20.342782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Cross Modal Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alessandro Calefati, Ignazio Gallo, Muhammad Kamran Janjua, Shah Nawaz","submitted_at":"2018-07-19T12:35:24Z","abstract_excerpt":"This paper proposes a cross-modal retrieval system that leverages on image and text encoding. Most multimodal architectures employ separate networks for each modality to capture the semantic relationship between them. However, in our work image-text encoding can achieve comparable results in terms of cross-modal retrieval without having to use a separate network for each modality. We show that text encodings can capture semantic relationships between multiple modalities. In our knowledge, this work is the first of its kind in terms of employing a single network and fused image-text embedding f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.07364","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":""},"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":"1807.07364","created_at":"2026-05-18T00:10:20.342843+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.07364v1","created_at":"2026-05-18T00:10:20.342843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.07364","created_at":"2026-05-18T00:10:20.342843+00:00"},{"alias_kind":"pith_short_12","alias_value":"CYAYXFETUQT6","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"CYAYXFETUQT65DVB","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"CYAYXFET","created_at":"2026-05-18T12:32:19.392346+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/CYAYXFETUQT65DVBNHREHVH7OM","json":"https://pith.science/pith/CYAYXFETUQT65DVBNHREHVH7OM.json","graph_json":"https://pith.science/api/pith-number/CYAYXFETUQT65DVBNHREHVH7OM/graph.json","events_json":"https://pith.science/api/pith-number/CYAYXFETUQT65DVBNHREHVH7OM/events.json","paper":"https://pith.science/paper/CYAYXFET"},"agent_actions":{"view_html":"https://pith.science/pith/CYAYXFETUQT65DVBNHREHVH7OM","download_json":"https://pith.science/pith/CYAYXFETUQT65DVBNHREHVH7OM.json","view_paper":"https://pith.science/paper/CYAYXFET","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.07364&json=true","fetch_graph":"https://pith.science/api/pith-number/CYAYXFETUQT65DVBNHREHVH7OM/graph.json","fetch_events":"https://pith.science/api/pith-number/CYAYXFETUQT65DVBNHREHVH7OM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CYAYXFETUQT65DVBNHREHVH7OM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CYAYXFETUQT65DVBNHREHVH7OM/action/storage_attestation","attest_author":"https://pith.science/pith/CYAYXFETUQT65DVBNHREHVH7OM/action/author_attestation","sign_citation":"https://pith.science/pith/CYAYXFETUQT65DVBNHREHVH7OM/action/citation_signature","submit_replication":"https://pith.science/pith/CYAYXFETUQT65DVBNHREHVH7OM/action/replication_record"}},"created_at":"2026-05-18T00:10:20.342843+00:00","updated_at":"2026-05-18T00:10:20.342843+00:00"}