{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:MHNYWRU4M42BFZOQARLJRFK3IE","short_pith_number":"pith:MHNYWRU4","schema_version":"1.0","canonical_sha256":"61db8b469c673412e5d0045698955b41188d70bff3beb3630e9e5af195a9d06d","source":{"kind":"arxiv","id":"1707.07601","version":1},"attestation_state":"computed","paper":{"title":"Image Pivoting for Learning Multilingual Multimodal Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Frank Keller, Mirella Lapata, Rico Sennrich, Spandana Gella","submitted_at":"2017-07-24T15:08:13Z","abstract_excerpt":"In this paper we propose a model to learn multimodal multilingual representations for matching images and sentences in different languages, with the aim of advancing multilingual versions of image search and image understanding. Our model learns a common representation for images and their descriptions in two different languages (which need not be parallel) by considering the image as a pivot between two languages. We introduce a new pairwise ranking loss function which can handle both symmetric and asymmetric similarity between the two modalities. We evaluate our models on image-description r"},"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":"1707.07601","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-07-24T15:08:13Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c705e43c1bf8bd80c3a156c07c19dbcd8aa20e33555c33a7cd9d91233375b812","abstract_canon_sha256":"fc89a5b16f0fdcd8fd16f3dabc62928ac849d82ad1d5eedb80a1e03332e01cdd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:41.689662Z","signature_b64":"y8dJZTkEvjKznmB9LfCFSCP5Tr7LrwS3QbE99YeFQ/4NSf0Fy0gUTzaXS3NZTI+NIRVaCQNX3zmKyhelvWdIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61db8b469c673412e5d0045698955b41188d70bff3beb3630e9e5af195a9d06d","last_reissued_at":"2026-05-18T00:39:41.688998Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:41.688998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Pivoting for Learning Multilingual Multimodal Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Frank Keller, Mirella Lapata, Rico Sennrich, Spandana Gella","submitted_at":"2017-07-24T15:08:13Z","abstract_excerpt":"In this paper we propose a model to learn multimodal multilingual representations for matching images and sentences in different languages, with the aim of advancing multilingual versions of image search and image understanding. Our model learns a common representation for images and their descriptions in two different languages (which need not be parallel) by considering the image as a pivot between two languages. We introduce a new pairwise ranking loss function which can handle both symmetric and asymmetric similarity between the two modalities. We evaluate our models on image-description r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.07601","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":"1707.07601","created_at":"2026-05-18T00:39:41.689093+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.07601v1","created_at":"2026-05-18T00:39:41.689093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.07601","created_at":"2026-05-18T00:39:41.689093+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHNYWRU4M42B","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHNYWRU4M42BFZOQ","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHNYWRU4","created_at":"2026-05-18T12:31:31.346846+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/MHNYWRU4M42BFZOQARLJRFK3IE","json":"https://pith.science/pith/MHNYWRU4M42BFZOQARLJRFK3IE.json","graph_json":"https://pith.science/api/pith-number/MHNYWRU4M42BFZOQARLJRFK3IE/graph.json","events_json":"https://pith.science/api/pith-number/MHNYWRU4M42BFZOQARLJRFK3IE/events.json","paper":"https://pith.science/paper/MHNYWRU4"},"agent_actions":{"view_html":"https://pith.science/pith/MHNYWRU4M42BFZOQARLJRFK3IE","download_json":"https://pith.science/pith/MHNYWRU4M42BFZOQARLJRFK3IE.json","view_paper":"https://pith.science/paper/MHNYWRU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.07601&json=true","fetch_graph":"https://pith.science/api/pith-number/MHNYWRU4M42BFZOQARLJRFK3IE/graph.json","fetch_events":"https://pith.science/api/pith-number/MHNYWRU4M42BFZOQARLJRFK3IE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHNYWRU4M42BFZOQARLJRFK3IE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHNYWRU4M42BFZOQARLJRFK3IE/action/storage_attestation","attest_author":"https://pith.science/pith/MHNYWRU4M42BFZOQARLJRFK3IE/action/author_attestation","sign_citation":"https://pith.science/pith/MHNYWRU4M42BFZOQARLJRFK3IE/action/citation_signature","submit_replication":"https://pith.science/pith/MHNYWRU4M42BFZOQARLJRFK3IE/action/replication_record"}},"created_at":"2026-05-18T00:39:41.689093+00:00","updated_at":"2026-05-18T00:39:41.689093+00:00"}