{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G7LIASRI3KQMMX2XIU5EONEMPF","short_pith_number":"pith:G7LIASRI","schema_version":"1.0","canonical_sha256":"37d6804a28daa0c65f57453a47348c7956e20c168584995abccda4850bb2af52","source":{"kind":"arxiv","id":"2405.12710","version":3},"attestation_state":"computed","paper":{"title":"Text-Video Retrieval with Global-Local Semantic Consistent Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haonan Zhang, Hengtao Shen, Jingkuan Song, Lianli Gao, Pengpeng Zeng, Xinyu Lyu, Yihang Duan","submitted_at":"2024-05-21T11:59:36Z","abstract_excerpt":"Adapting large-scale image-text pre-training models, e.g., CLIP, to the video domain represents the current state-of-the-art for text-video retrieval. The primary approaches involve transferring text-video pairs to a common embedding space and leveraging cross-modal interactions on specific entities for semantic alignment. Though effective, these paradigms entail prohibitive computational costs, leading to inefficient retrieval. To address this, we propose a simple yet effective method, Global-Local Semantic Consistent Learning (GLSCL), which capitalizes on latent shared semantics across modal"},"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":"2405.12710","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-21T11:59:36Z","cross_cats_sorted":[],"title_canon_sha256":"8504acbc924d3bb77baa4497570d52dd40e6a68f7a910e26b423e7d5b4ea9e2e","abstract_canon_sha256":"a745bdf37cbfd270a37edc9124f8ba3f0c8ec16dd0feff5451709a3259ac9dc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:14.353340Z","signature_b64":"TEjb0lzjZjip+BwdDJpVdJy5qFUOhugxXQJDOBJJ75o4hGrw4TJR50GRKpJPVuWCunTexSHEoPHJtvYPnRYrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37d6804a28daa0c65f57453a47348c7956e20c168584995abccda4850bb2af52","last_reissued_at":"2026-07-05T08:44:14.352898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:14.352898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-Video Retrieval with Global-Local Semantic Consistent Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haonan Zhang, Hengtao Shen, Jingkuan Song, Lianli Gao, Pengpeng Zeng, Xinyu Lyu, Yihang Duan","submitted_at":"2024-05-21T11:59:36Z","abstract_excerpt":"Adapting large-scale image-text pre-training models, e.g., CLIP, to the video domain represents the current state-of-the-art for text-video retrieval. The primary approaches involve transferring text-video pairs to a common embedding space and leveraging cross-modal interactions on specific entities for semantic alignment. Though effective, these paradigms entail prohibitive computational costs, leading to inefficient retrieval. To address this, we propose a simple yet effective method, Global-Local Semantic Consistent Learning (GLSCL), which capitalizes on latent shared semantics across modal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12710","kind":"arxiv","version":3},"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/2405.12710/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":"2405.12710","created_at":"2026-07-05T08:44:14.352954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12710v3","created_at":"2026-07-05T08:44:14.352954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12710","created_at":"2026-07-05T08:44:14.352954+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7LIASRI3KQM","created_at":"2026-07-05T08:44:14.352954+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7LIASRI3KQMMX2X","created_at":"2026-07-05T08:44:14.352954+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7LIASRI","created_at":"2026-07-05T08:44:14.352954+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/G7LIASRI3KQMMX2XIU5EONEMPF","json":"https://pith.science/pith/G7LIASRI3KQMMX2XIU5EONEMPF.json","graph_json":"https://pith.science/api/pith-number/G7LIASRI3KQMMX2XIU5EONEMPF/graph.json","events_json":"https://pith.science/api/pith-number/G7LIASRI3KQMMX2XIU5EONEMPF/events.json","paper":"https://pith.science/paper/G7LIASRI"},"agent_actions":{"view_html":"https://pith.science/pith/G7LIASRI3KQMMX2XIU5EONEMPF","download_json":"https://pith.science/pith/G7LIASRI3KQMMX2XIU5EONEMPF.json","view_paper":"https://pith.science/paper/G7LIASRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12710&json=true","fetch_graph":"https://pith.science/api/pith-number/G7LIASRI3KQMMX2XIU5EONEMPF/graph.json","fetch_events":"https://pith.science/api/pith-number/G7LIASRI3KQMMX2XIU5EONEMPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7LIASRI3KQMMX2XIU5EONEMPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7LIASRI3KQMMX2XIU5EONEMPF/action/storage_attestation","attest_author":"https://pith.science/pith/G7LIASRI3KQMMX2XIU5EONEMPF/action/author_attestation","sign_citation":"https://pith.science/pith/G7LIASRI3KQMMX2XIU5EONEMPF/action/citation_signature","submit_replication":"https://pith.science/pith/G7LIASRI3KQMMX2XIU5EONEMPF/action/replication_record"}},"created_at":"2026-07-05T08:44:14.352954+00:00","updated_at":"2026-07-05T08:44:14.352954+00:00"}