{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ESYHCMZSYZEIQ43PWJN2EPTRIT","short_pith_number":"pith:ESYHCMZS","schema_version":"1.0","canonical_sha256":"24b0713332c64888736fb25ba23e7144e65bdea7169d1d27f78b2c8402c00007","source":{"kind":"arxiv","id":"2205.12105","version":2},"attestation_state":"computed","paper":{"title":"HiVLP: Hierarchical Vision-Language Pre-Training for Fast Image-Text Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Duzhen Zhang, Feilong Chen, Jianlong Chang, Jiaxin Shi, Qi Tian, Xiuyi Chen","submitted_at":"2022-05-24T14:32:57Z","abstract_excerpt":"In the past few years, the emergence of vision-language pre-training (VLP) has brought cross-modal retrieval to a new era. However, due to the latency and computation demand, it is commonly challenging to apply VLP in a real-time online retrieval system. To alleviate the defect, this paper proposes a \\textbf{Hi}erarchical \\textbf{V}ision-\\textbf{}Language \\textbf{P}re-Training (\\textbf{HiVLP}) for fast Image-Text Retrieval (ITR). Specifically, we design a novel hierarchical retrieval objective, which uses the representation of different dimensions for coarse-to-fine ITR, i.e., using low-dimens"},"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":"2205.12105","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-24T14:32:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"87effe95b59e3d594476ef1ae2b74528378e06358003739fcac3491ff64b22d1","abstract_canon_sha256":"9dafc0c5726fbc4c7a66326ce3beb4dc369df9d80395a754b4652df00e59ab5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:31.410520Z","signature_b64":"sXFCdfLFbmmZVNXpcxBSZQZ0OeW5E0knMEu01ovw3bEHaGoVVrpVYfP2Wgd2+EYfHHyu67IFD/ZwYSTo2Sh+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24b0713332c64888736fb25ba23e7144e65bdea7169d1d27f78b2c8402c00007","last_reissued_at":"2026-07-05T04:27:31.410031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:31.410031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiVLP: Hierarchical Vision-Language Pre-Training for Fast Image-Text Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Duzhen Zhang, Feilong Chen, Jianlong Chang, Jiaxin Shi, Qi Tian, Xiuyi Chen","submitted_at":"2022-05-24T14:32:57Z","abstract_excerpt":"In the past few years, the emergence of vision-language pre-training (VLP) has brought cross-modal retrieval to a new era. However, due to the latency and computation demand, it is commonly challenging to apply VLP in a real-time online retrieval system. To alleviate the defect, this paper proposes a \\textbf{Hi}erarchical \\textbf{V}ision-\\textbf{}Language \\textbf{P}re-Training (\\textbf{HiVLP}) for fast Image-Text Retrieval (ITR). Specifically, we design a novel hierarchical retrieval objective, which uses the representation of different dimensions for coarse-to-fine ITR, i.e., using low-dimens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12105","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.12105/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":"2205.12105","created_at":"2026-07-05T04:27:31.410081+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.12105v2","created_at":"2026-07-05T04:27:31.410081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12105","created_at":"2026-07-05T04:27:31.410081+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESYHCMZSYZEI","created_at":"2026-07-05T04:27:31.410081+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESYHCMZSYZEIQ43P","created_at":"2026-07-05T04:27:31.410081+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESYHCMZS","created_at":"2026-07-05T04:27:31.410081+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/ESYHCMZSYZEIQ43PWJN2EPTRIT","json":"https://pith.science/pith/ESYHCMZSYZEIQ43PWJN2EPTRIT.json","graph_json":"https://pith.science/api/pith-number/ESYHCMZSYZEIQ43PWJN2EPTRIT/graph.json","events_json":"https://pith.science/api/pith-number/ESYHCMZSYZEIQ43PWJN2EPTRIT/events.json","paper":"https://pith.science/paper/ESYHCMZS"},"agent_actions":{"view_html":"https://pith.science/pith/ESYHCMZSYZEIQ43PWJN2EPTRIT","download_json":"https://pith.science/pith/ESYHCMZSYZEIQ43PWJN2EPTRIT.json","view_paper":"https://pith.science/paper/ESYHCMZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.12105&json=true","fetch_graph":"https://pith.science/api/pith-number/ESYHCMZSYZEIQ43PWJN2EPTRIT/graph.json","fetch_events":"https://pith.science/api/pith-number/ESYHCMZSYZEIQ43PWJN2EPTRIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESYHCMZSYZEIQ43PWJN2EPTRIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESYHCMZSYZEIQ43PWJN2EPTRIT/action/storage_attestation","attest_author":"https://pith.science/pith/ESYHCMZSYZEIQ43PWJN2EPTRIT/action/author_attestation","sign_citation":"https://pith.science/pith/ESYHCMZSYZEIQ43PWJN2EPTRIT/action/citation_signature","submit_replication":"https://pith.science/pith/ESYHCMZSYZEIQ43PWJN2EPTRIT/action/replication_record"}},"created_at":"2026-07-05T04:27:31.410081+00:00","updated_at":"2026-07-05T04:27:31.410081+00:00"}