{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DNT7PND36BBKQQ63Z6CD2WAG7A","short_pith_number":"pith:DNT7PND3","schema_version":"1.0","canonical_sha256":"1b67f7b47bf042a843dbcf843d5806f8166b4367af09a79ee70cd05e6fb4bb77","source":{"kind":"arxiv","id":"1904.05521","version":2},"attestation_state":"computed","paper":{"title":"UniVSE: Robust Visual Semantic Embeddings via Structured Semantic Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Wu, Jiayuan Mao, Lei Li, Weiwei Sun, Wei-Ying Ma, Yufeng Zhang, Yuning Jiang","submitted_at":"2019-04-11T04:04:06Z","abstract_excerpt":"We propose Unified Visual-Semantic Embeddings (UniVSE) for learning a joint space of visual and textual concepts. The space unifies the concepts at different levels, including objects, attributes, relations, and full scenes. A contrastive learning approach is proposed for the fine-grained alignment from only image-caption pairs. Moreover, we present an effective approach for enforcing the coverage of semantic components that appear in the sentence. We demonstrate the robustness of Unified VSE in defending text-domain adversarial attacks on cross-modal retrieval tasks. Such robustness also empo"},"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":"1904.05521","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-11T04:04:06Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"f2dc2394a25cabe6983d8e096d7c2d22f6239bea83deb6c1c78eec3286fe1f69","abstract_canon_sha256":"be6b8dce737581b9578f01890afca72c52faa62b850bf4a4e7a228ba4a1a9020"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:39.221568Z","signature_b64":"sed3EqatQoVXd4FDmxZoYXCa1HJh6/OQFm1KPfnZXOgLV5ALqjB+1JcmVE1Gtd4B4X8Q97neyElBYhq3L2ugCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b67f7b47bf042a843dbcf843d5806f8166b4367af09a79ee70cd05e6fb4bb77","last_reissued_at":"2026-05-17T23:47:39.221146Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:39.221146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniVSE: Robust Visual Semantic Embeddings via Structured Semantic Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Wu, Jiayuan Mao, Lei Li, Weiwei Sun, Wei-Ying Ma, Yufeng Zhang, Yuning Jiang","submitted_at":"2019-04-11T04:04:06Z","abstract_excerpt":"We propose Unified Visual-Semantic Embeddings (UniVSE) for learning a joint space of visual and textual concepts. The space unifies the concepts at different levels, including objects, attributes, relations, and full scenes. A contrastive learning approach is proposed for the fine-grained alignment from only image-caption pairs. Moreover, we present an effective approach for enforcing the coverage of semantic components that appear in the sentence. We demonstrate the robustness of Unified VSE in defending text-domain adversarial attacks on cross-modal retrieval tasks. Such robustness also empo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.05521","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":"1904.05521","created_at":"2026-05-17T23:47:39.221218+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.05521v2","created_at":"2026-05-17T23:47:39.221218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.05521","created_at":"2026-05-17T23:47:39.221218+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNT7PND36BBK","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNT7PND36BBKQQ63","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNT7PND3","created_at":"2026-05-18T12:33:15.570797+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/DNT7PND36BBKQQ63Z6CD2WAG7A","json":"https://pith.science/pith/DNT7PND36BBKQQ63Z6CD2WAG7A.json","graph_json":"https://pith.science/api/pith-number/DNT7PND36BBKQQ63Z6CD2WAG7A/graph.json","events_json":"https://pith.science/api/pith-number/DNT7PND36BBKQQ63Z6CD2WAG7A/events.json","paper":"https://pith.science/paper/DNT7PND3"},"agent_actions":{"view_html":"https://pith.science/pith/DNT7PND36BBKQQ63Z6CD2WAG7A","download_json":"https://pith.science/pith/DNT7PND36BBKQQ63Z6CD2WAG7A.json","view_paper":"https://pith.science/paper/DNT7PND3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.05521&json=true","fetch_graph":"https://pith.science/api/pith-number/DNT7PND36BBKQQ63Z6CD2WAG7A/graph.json","fetch_events":"https://pith.science/api/pith-number/DNT7PND36BBKQQ63Z6CD2WAG7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNT7PND36BBKQQ63Z6CD2WAG7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNT7PND36BBKQQ63Z6CD2WAG7A/action/storage_attestation","attest_author":"https://pith.science/pith/DNT7PND36BBKQQ63Z6CD2WAG7A/action/author_attestation","sign_citation":"https://pith.science/pith/DNT7PND36BBKQQ63Z6CD2WAG7A/action/citation_signature","submit_replication":"https://pith.science/pith/DNT7PND36BBKQQ63Z6CD2WAG7A/action/replication_record"}},"created_at":"2026-05-17T23:47:39.221218+00:00","updated_at":"2026-05-17T23:47:39.221218+00:00"}