{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5CYV2VECFS42IKYNKUMNQRGHRL","short_pith_number":"pith:5CYV2VEC","schema_version":"1.0","canonical_sha256":"e8b15d54822cb9a42b0d5518d844c78adede766ac56ce2c96aa14acf8a39d61e","source":{"kind":"arxiv","id":"2203.14713","version":3},"attestation_state":"computed","paper":{"title":"Image-text Retrieval: A Survey on Recent Research and Development","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Juntao Li, Liqiang Nie, Min Cao, Min Zhang, Shiping Li","submitted_at":"2022-03-28T13:00:01Z","abstract_excerpt":"In the past few years, cross-modal image-text retrieval (ITR) has experienced increased interest in the research community due to its excellent research value and broad real-world application. It is designed for the scenarios where the queries are from one modality and the retrieval galleries from another modality. This paper presents a comprehensive and up-to-date survey on the ITR approaches from four perspectives. By dissecting an ITR system into two processes: feature extraction and feature alignment, we summarize the recent advance of the ITR approaches from these two perspectives. On top"},"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":"2203.14713","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-03-28T13:00:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2dd139c159539f94f9d6f9a4d0bf5b4004fc73dae3def202cd7bb61b00d66a36","abstract_canon_sha256":"bc3caa59e22b7baf851e97373ca069030517c28eab76b8023f922a2fe32b8669"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:10.060340Z","signature_b64":"pLigmESgUl1u6Wf5jh/rqh6ggVT/U9k9szDNYwXWXkVdxvVU+GLABoLTxjlPRRh4b3KPTlk9ynFaeW9dDwiQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8b15d54822cb9a42b0d5518d844c78adede766ac56ce2c96aa14acf8a39d61e","last_reissued_at":"2026-07-05T05:17:10.059894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:10.059894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image-text Retrieval: A Survey on Recent Research and Development","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Juntao Li, Liqiang Nie, Min Cao, Min Zhang, Shiping Li","submitted_at":"2022-03-28T13:00:01Z","abstract_excerpt":"In the past few years, cross-modal image-text retrieval (ITR) has experienced increased interest in the research community due to its excellent research value and broad real-world application. It is designed for the scenarios where the queries are from one modality and the retrieval galleries from another modality. This paper presents a comprehensive and up-to-date survey on the ITR approaches from four perspectives. By dissecting an ITR system into two processes: feature extraction and feature alignment, we summarize the recent advance of the ITR approaches from these two perspectives. On top"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14713","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/2203.14713/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":"2203.14713","created_at":"2026-07-05T05:17:10.059950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.14713v3","created_at":"2026-07-05T05:17:10.059950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14713","created_at":"2026-07-05T05:17:10.059950+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CYV2VECFS42","created_at":"2026-07-05T05:17:10.059950+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CYV2VECFS42IKYN","created_at":"2026-07-05T05:17:10.059950+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CYV2VEC","created_at":"2026-07-05T05:17:10.059950+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11496","citing_title":"Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5CYV2VECFS42IKYNKUMNQRGHRL","json":"https://pith.science/pith/5CYV2VECFS42IKYNKUMNQRGHRL.json","graph_json":"https://pith.science/api/pith-number/5CYV2VECFS42IKYNKUMNQRGHRL/graph.json","events_json":"https://pith.science/api/pith-number/5CYV2VECFS42IKYNKUMNQRGHRL/events.json","paper":"https://pith.science/paper/5CYV2VEC"},"agent_actions":{"view_html":"https://pith.science/pith/5CYV2VECFS42IKYNKUMNQRGHRL","download_json":"https://pith.science/pith/5CYV2VECFS42IKYNKUMNQRGHRL.json","view_paper":"https://pith.science/paper/5CYV2VEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.14713&json=true","fetch_graph":"https://pith.science/api/pith-number/5CYV2VECFS42IKYNKUMNQRGHRL/graph.json","fetch_events":"https://pith.science/api/pith-number/5CYV2VECFS42IKYNKUMNQRGHRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CYV2VECFS42IKYNKUMNQRGHRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CYV2VECFS42IKYNKUMNQRGHRL/action/storage_attestation","attest_author":"https://pith.science/pith/5CYV2VECFS42IKYNKUMNQRGHRL/action/author_attestation","sign_citation":"https://pith.science/pith/5CYV2VECFS42IKYNKUMNQRGHRL/action/citation_signature","submit_replication":"https://pith.science/pith/5CYV2VECFS42IKYNKUMNQRGHRL/action/replication_record"}},"created_at":"2026-07-05T05:17:10.059950+00:00","updated_at":"2026-07-05T05:17:10.059950+00:00"}