{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2F76QRCNNOR5TOAA46TAYU2HQF","short_pith_number":"pith:2F76QRCN","schema_version":"1.0","canonical_sha256":"d17fe8444d6ba3d9b800e7a60c53478170a58d21321e178751724fccfd35d6d4","source":{"kind":"arxiv","id":"1905.13339","version":1},"attestation_state":"computed","paper":{"title":"Multitask Text-to-Visual Embedding with Titles and Clickthrough Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Baldo Faieta, Pranav Aggarwal, Saeid Motiian, Zhe Lin","submitted_at":"2019-05-30T22:33:15Z","abstract_excerpt":"Text-visual (or called semantic-visual) embedding is a central problem in vision-language research. It typically involves mapping of an image and a text description to a common feature space through a CNN image encoder and a RNN language encoder. In this paper, we propose a new method for learning text-visual embedding using both image titles and click-through data from an image search engine. We also propose a new triplet loss function by modeling positive awareness of the embedding, and introduce a novel mini-batch-based hard negative sampling approach for better data efficiency in the learn"},"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":"1905.13339","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-05-30T22:33:15Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"39264cdca53deb8f964c428adb002bd9891b1266bc80f80b16e1469a4f2467df","abstract_canon_sha256":"2e0bb97828af18fb5c2f9d8db17e9067f70c87e6a34518ec6b25ca7a394b5175"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:35.251645Z","signature_b64":"WnUfK5DcdroUpQak6wRU0QzmEFrETbl/ZbuRr/bLW92HTQRMkqaFEry3IhfRYfMLnDh5gFZgBqMr/p22RgaNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d17fe8444d6ba3d9b800e7a60c53478170a58d21321e178751724fccfd35d6d4","last_reissued_at":"2026-05-17T23:44:35.251179Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:35.251179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multitask Text-to-Visual Embedding with Titles and Clickthrough Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Baldo Faieta, Pranav Aggarwal, Saeid Motiian, Zhe Lin","submitted_at":"2019-05-30T22:33:15Z","abstract_excerpt":"Text-visual (or called semantic-visual) embedding is a central problem in vision-language research. It typically involves mapping of an image and a text description to a common feature space through a CNN image encoder and a RNN language encoder. In this paper, we propose a new method for learning text-visual embedding using both image titles and click-through data from an image search engine. We also propose a new triplet loss function by modeling positive awareness of the embedding, and introduce a novel mini-batch-based hard negative sampling approach for better data efficiency in the learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13339","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":"1905.13339","created_at":"2026-05-17T23:44:35.251241+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13339v1","created_at":"2026-05-17T23:44:35.251241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13339","created_at":"2026-05-17T23:44:35.251241+00:00"},{"alias_kind":"pith_short_12","alias_value":"2F76QRCNNOR5","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2F76QRCNNOR5TOAA","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2F76QRCN","created_at":"2026-05-18T12:33:07.085635+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/2F76QRCNNOR5TOAA46TAYU2HQF","json":"https://pith.science/pith/2F76QRCNNOR5TOAA46TAYU2HQF.json","graph_json":"https://pith.science/api/pith-number/2F76QRCNNOR5TOAA46TAYU2HQF/graph.json","events_json":"https://pith.science/api/pith-number/2F76QRCNNOR5TOAA46TAYU2HQF/events.json","paper":"https://pith.science/paper/2F76QRCN"},"agent_actions":{"view_html":"https://pith.science/pith/2F76QRCNNOR5TOAA46TAYU2HQF","download_json":"https://pith.science/pith/2F76QRCNNOR5TOAA46TAYU2HQF.json","view_paper":"https://pith.science/paper/2F76QRCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13339&json=true","fetch_graph":"https://pith.science/api/pith-number/2F76QRCNNOR5TOAA46TAYU2HQF/graph.json","fetch_events":"https://pith.science/api/pith-number/2F76QRCNNOR5TOAA46TAYU2HQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2F76QRCNNOR5TOAA46TAYU2HQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2F76QRCNNOR5TOAA46TAYU2HQF/action/storage_attestation","attest_author":"https://pith.science/pith/2F76QRCNNOR5TOAA46TAYU2HQF/action/author_attestation","sign_citation":"https://pith.science/pith/2F76QRCNNOR5TOAA46TAYU2HQF/action/citation_signature","submit_replication":"https://pith.science/pith/2F76QRCNNOR5TOAA46TAYU2HQF/action/replication_record"}},"created_at":"2026-05-17T23:44:35.251241+00:00","updated_at":"2026-05-17T23:44:35.251241+00:00"}