{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6G23K53Z5KXQOXPFJ2DXDQXY5U","short_pith_number":"pith:6G23K53Z","schema_version":"1.0","canonical_sha256":"f1b5b57779eaaf075de54e8771c2f8ed3330dc8fb931619d9e5837bd1dcd48d8","source":{"kind":"arxiv","id":"2402.16769","version":1},"attestation_state":"computed","paper":{"title":"Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Li, Chenliang Li, Chunfeng Yuan, Fei Huang, Haiyang Xu, Haowei Liu, Ji Zhang, Ming Yan, Qinghao Ye, Weiming Hu, Yaya Shi","submitted_at":"2024-02-26T17:36:50Z","abstract_excerpt":"In video-text retrieval, most existing methods adopt the dual-encoder architecture for fast retrieval, which employs two individual encoders to extract global latent representations for videos and texts. However, they face challenges in capturing fine-grained semantic concepts. In this work, we propose the UNIFY framework, which learns lexicon representations to capture fine-grained semantics and combines the strengths of latent and lexicon representations for video-text retrieval. Specifically, we map videos and texts into a pre-defined lexicon space, where each dimension corresponds to a sem"},"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":"2402.16769","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-26T17:36:50Z","cross_cats_sorted":[],"title_canon_sha256":"8510a3811601decc89964b7dffe9eb860c4ef269217d4ab4e11c6439768f8908","abstract_canon_sha256":"4b8afa50fabdd8c96b49e8085a83fedde72dedfd4a53df85e9e312f4ecbd381c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:26.121965Z","signature_b64":"iWo6P9LN/2dLWsb2z/7oSPw79/93Z0z8DD1CjfxW3jA2eMegHKT6qTxS4EdbXY77/KVagwCSFgoYaZkmWFuOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1b5b57779eaaf075de54e8771c2f8ed3330dc8fb931619d9e5837bd1dcd48d8","last_reissued_at":"2026-07-05T07:49:26.121472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:26.121472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Li, Chenliang Li, Chunfeng Yuan, Fei Huang, Haiyang Xu, Haowei Liu, Ji Zhang, Ming Yan, Qinghao Ye, Weiming Hu, Yaya Shi","submitted_at":"2024-02-26T17:36:50Z","abstract_excerpt":"In video-text retrieval, most existing methods adopt the dual-encoder architecture for fast retrieval, which employs two individual encoders to extract global latent representations for videos and texts. However, they face challenges in capturing fine-grained semantic concepts. In this work, we propose the UNIFY framework, which learns lexicon representations to capture fine-grained semantics and combines the strengths of latent and lexicon representations for video-text retrieval. Specifically, we map videos and texts into a pre-defined lexicon space, where each dimension corresponds to a sem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16769","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.16769/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2402.16769","created_at":"2026-07-05T07:49:26.121533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16769v1","created_at":"2026-07-05T07:49:26.121533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16769","created_at":"2026-07-05T07:49:26.121533+00:00"},{"alias_kind":"pith_short_12","alias_value":"6G23K53Z5KXQ","created_at":"2026-07-05T07:49:26.121533+00:00"},{"alias_kind":"pith_short_16","alias_value":"6G23K53Z5KXQOXPF","created_at":"2026-07-05T07:49:26.121533+00:00"},{"alias_kind":"pith_short_8","alias_value":"6G23K53Z","created_at":"2026-07-05T07:49:26.121533+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/6G23K53Z5KXQOXPFJ2DXDQXY5U","json":"https://pith.science/pith/6G23K53Z5KXQOXPFJ2DXDQXY5U.json","graph_json":"https://pith.science/api/pith-number/6G23K53Z5KXQOXPFJ2DXDQXY5U/graph.json","events_json":"https://pith.science/api/pith-number/6G23K53Z5KXQOXPFJ2DXDQXY5U/events.json","paper":"https://pith.science/paper/6G23K53Z"},"agent_actions":{"view_html":"https://pith.science/pith/6G23K53Z5KXQOXPFJ2DXDQXY5U","download_json":"https://pith.science/pith/6G23K53Z5KXQOXPFJ2DXDQXY5U.json","view_paper":"https://pith.science/paper/6G23K53Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16769&json=true","fetch_graph":"https://pith.science/api/pith-number/6G23K53Z5KXQOXPFJ2DXDQXY5U/graph.json","fetch_events":"https://pith.science/api/pith-number/6G23K53Z5KXQOXPFJ2DXDQXY5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6G23K53Z5KXQOXPFJ2DXDQXY5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6G23K53Z5KXQOXPFJ2DXDQXY5U/action/storage_attestation","attest_author":"https://pith.science/pith/6G23K53Z5KXQOXPFJ2DXDQXY5U/action/author_attestation","sign_citation":"https://pith.science/pith/6G23K53Z5KXQOXPFJ2DXDQXY5U/action/citation_signature","submit_replication":"https://pith.science/pith/6G23K53Z5KXQOXPFJ2DXDQXY5U/action/replication_record"}},"created_at":"2026-07-05T07:49:26.121533+00:00","updated_at":"2026-07-05T07:49:26.121533+00:00"}