{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:22DFHOP4KGAEACWVQLK7UBZ3FB","short_pith_number":"pith:22DFHOP4","schema_version":"1.0","canonical_sha256":"d68653b9fc5180400ad582d5fa073b284cb70a2b546464add5834c00a33549b0","source":{"kind":"arxiv","id":"2407.06001","version":2},"attestation_state":"computed","paper":{"title":"Pseudo-triplet Guided Few-shot Composed Image Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bohan Hou, Haokun Wen, Haoqiang Lin, Meng Liu, Mingzhu Xu, Xuemeng Song","submitted_at":"2024-07-08T14:53:07Z","abstract_excerpt":"Composed Image Retrieval (CIR) is a challenging task that aims to retrieve the target image with a multimodal query, i.e., a reference image, and its complementary modification text. As previous supervised or zero-shot learning paradigms all fail to strike a good trade-off between the model's generalization ability and retrieval performance, recent researchers have introduced the task of few-shot CIR (FS-CIR) and proposed a textual inversion-based network based on pretrained CLIP model to realize it. Despite its promising performance, the approach encounters two key limitations: simply relying"},"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":"2407.06001","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T14:53:07Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"45cba533cfb6509e96b0e1b32913daa73551d5f3f527f4f51a9756fc99cf699f","abstract_canon_sha256":"112c69c8b1ea11118a0865326c90bd8cdc42d3de124a8719674561262c2a18b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:15.950926Z","signature_b64":"AT0p8E81vh2s+yibX85Drpsq5WD5pNoowsDVAzYynNUcKUBe+2/mvL/WCz/bbnnDHcdNw0isAA2FHLXZWQLWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d68653b9fc5180400ad582d5fa073b284cb70a2b546464add5834c00a33549b0","last_reissued_at":"2026-07-05T09:34:15.950401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:15.950401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pseudo-triplet Guided Few-shot Composed Image Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bohan Hou, Haokun Wen, Haoqiang Lin, Meng Liu, Mingzhu Xu, Xuemeng Song","submitted_at":"2024-07-08T14:53:07Z","abstract_excerpt":"Composed Image Retrieval (CIR) is a challenging task that aims to retrieve the target image with a multimodal query, i.e., a reference image, and its complementary modification text. As previous supervised or zero-shot learning paradigms all fail to strike a good trade-off between the model's generalization ability and retrieval performance, recent researchers have introduced the task of few-shot CIR (FS-CIR) and proposed a textual inversion-based network based on pretrained CLIP model to realize it. Despite its promising performance, the approach encounters two key limitations: simply relying"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06001","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/2407.06001/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":"2407.06001","created_at":"2026-07-05T09:34:15.950463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.06001v2","created_at":"2026-07-05T09:34:15.950463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06001","created_at":"2026-07-05T09:34:15.950463+00:00"},{"alias_kind":"pith_short_12","alias_value":"22DFHOP4KGAE","created_at":"2026-07-05T09:34:15.950463+00:00"},{"alias_kind":"pith_short_16","alias_value":"22DFHOP4KGAEACWV","created_at":"2026-07-05T09:34:15.950463+00:00"},{"alias_kind":"pith_short_8","alias_value":"22DFHOP4","created_at":"2026-07-05T09:34:15.950463+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17796","citing_title":"DetailFusion: A Dual-branch Framework with Detail Enhancement for Composed Image Retrieval","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/22DFHOP4KGAEACWVQLK7UBZ3FB","json":"https://pith.science/pith/22DFHOP4KGAEACWVQLK7UBZ3FB.json","graph_json":"https://pith.science/api/pith-number/22DFHOP4KGAEACWVQLK7UBZ3FB/graph.json","events_json":"https://pith.science/api/pith-number/22DFHOP4KGAEACWVQLK7UBZ3FB/events.json","paper":"https://pith.science/paper/22DFHOP4"},"agent_actions":{"view_html":"https://pith.science/pith/22DFHOP4KGAEACWVQLK7UBZ3FB","download_json":"https://pith.science/pith/22DFHOP4KGAEACWVQLK7UBZ3FB.json","view_paper":"https://pith.science/paper/22DFHOP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.06001&json=true","fetch_graph":"https://pith.science/api/pith-number/22DFHOP4KGAEACWVQLK7UBZ3FB/graph.json","fetch_events":"https://pith.science/api/pith-number/22DFHOP4KGAEACWVQLK7UBZ3FB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22DFHOP4KGAEACWVQLK7UBZ3FB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22DFHOP4KGAEACWVQLK7UBZ3FB/action/storage_attestation","attest_author":"https://pith.science/pith/22DFHOP4KGAEACWVQLK7UBZ3FB/action/author_attestation","sign_citation":"https://pith.science/pith/22DFHOP4KGAEACWVQLK7UBZ3FB/action/citation_signature","submit_replication":"https://pith.science/pith/22DFHOP4KGAEACWVQLK7UBZ3FB/action/replication_record"}},"created_at":"2026-07-05T09:34:15.950463+00:00","updated_at":"2026-07-05T09:34:15.950463+00:00"}