{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LGUG6X54TH74ZVLLC2EZBCYFR7","short_pith_number":"pith:LGUG6X54","schema_version":"1.0","canonical_sha256":"59a86f5fbc99ffccd56b1689908b058fdf81395cb1c83e6598533ada1e71fd50","source":{"kind":"arxiv","id":"1808.08266","version":2},"attestation_state":"computed","paper":{"title":"A Visual Attention Grounding Neural Model for Multimodal Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mingyang Zhou, Runxiang Cheng, Yong Jae Lee, Zhou Yu","submitted_at":"2018-08-24T18:47:29Z","abstract_excerpt":"We introduce a novel multimodal machine translation model that utilizes parallel visual and textual information. Our model jointly optimizes the learning of a shared visual-language embedding and a translator. The model leverages a visual attention grounding mechanism that links the visual semantics with the corresponding textual semantics. Our approach achieves competitive state-of-the-art results on the Multi30K and the Ambiguous COCO datasets. We also collected a new multilingual multimodal product description dataset to simulate a real-world international online shopping scenario. On this "},"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":"1808.08266","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-24T18:47:29Z","cross_cats_sorted":[],"title_canon_sha256":"49a09ea6d1b101fc0f4ec68cddf442b0f64a7c333dddb57c336208ea11977d02","abstract_canon_sha256":"306eeb2ae61d5ca998849b5f2f5e4b63ebc49b425ff215ff6a6cde54e90b79c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:05.136726Z","signature_b64":"vwCUcdhzS4fqTTHCxoBfjB9uSrcyzZKiCHz7WXFPS/jsrAU5YuAmYDNXPMZ1GcEVYOxykNz2BnXPAZWJKNKYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59a86f5fbc99ffccd56b1689908b058fdf81395cb1c83e6598533ada1e71fd50","last_reissued_at":"2026-05-18T00:07:05.135857Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:05.135857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Visual Attention Grounding Neural Model for Multimodal Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mingyang Zhou, Runxiang Cheng, Yong Jae Lee, Zhou Yu","submitted_at":"2018-08-24T18:47:29Z","abstract_excerpt":"We introduce a novel multimodal machine translation model that utilizes parallel visual and textual information. Our model jointly optimizes the learning of a shared visual-language embedding and a translator. The model leverages a visual attention grounding mechanism that links the visual semantics with the corresponding textual semantics. Our approach achieves competitive state-of-the-art results on the Multi30K and the Ambiguous COCO datasets. We also collected a new multilingual multimodal product description dataset to simulate a real-world international online shopping scenario. On this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08266","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":"1808.08266","created_at":"2026-05-18T00:07:05.136020+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.08266v2","created_at":"2026-05-18T00:07:05.136020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08266","created_at":"2026-05-18T00:07:05.136020+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGUG6X54TH74","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGUG6X54TH74ZVLL","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGUG6X54","created_at":"2026-05-18T12:32:37.024351+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/LGUG6X54TH74ZVLLC2EZBCYFR7","json":"https://pith.science/pith/LGUG6X54TH74ZVLLC2EZBCYFR7.json","graph_json":"https://pith.science/api/pith-number/LGUG6X54TH74ZVLLC2EZBCYFR7/graph.json","events_json":"https://pith.science/api/pith-number/LGUG6X54TH74ZVLLC2EZBCYFR7/events.json","paper":"https://pith.science/paper/LGUG6X54"},"agent_actions":{"view_html":"https://pith.science/pith/LGUG6X54TH74ZVLLC2EZBCYFR7","download_json":"https://pith.science/pith/LGUG6X54TH74ZVLLC2EZBCYFR7.json","view_paper":"https://pith.science/paper/LGUG6X54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.08266&json=true","fetch_graph":"https://pith.science/api/pith-number/LGUG6X54TH74ZVLLC2EZBCYFR7/graph.json","fetch_events":"https://pith.science/api/pith-number/LGUG6X54TH74ZVLLC2EZBCYFR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGUG6X54TH74ZVLLC2EZBCYFR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGUG6X54TH74ZVLLC2EZBCYFR7/action/storage_attestation","attest_author":"https://pith.science/pith/LGUG6X54TH74ZVLLC2EZBCYFR7/action/author_attestation","sign_citation":"https://pith.science/pith/LGUG6X54TH74ZVLLC2EZBCYFR7/action/citation_signature","submit_replication":"https://pith.science/pith/LGUG6X54TH74ZVLLC2EZBCYFR7/action/replication_record"}},"created_at":"2026-05-18T00:07:05.136020+00:00","updated_at":"2026-05-18T00:07:05.136020+00:00"}