{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UHFPTFMYUHXKEXIPOAHT7XH3X5","short_pith_number":"pith:UHFPTFMY","schema_version":"1.0","canonical_sha256":"a1caf99598a1eea25d0f700f3fdcfbbf63ce8f18c2c13b6b7a72d10e12172b3e","source":{"kind":"arxiv","id":"2410.17393","version":1},"attestation_state":"computed","paper":{"title":"Denoise-I2W: Mapping Images to Denoising Words for Accurate Zero-Shot Composed Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Xiong, Gaopeng Gou, Jiamin Zhuang, Jing Yu, Keke Gai, Qi Wu, Yuanmin Tang","submitted_at":"2024-10-22T20:01:00Z","abstract_excerpt":"Zero-Shot Composed Image Retrieval (ZS-CIR) supports diverse tasks with a broad range of visual content manipulation intentions that can be related to domain, scene, object, and attribute. A key challenge for ZS-CIR is to accurately map image representation to a pseudo-word token that captures the manipulation intention relevant image information for generalized CIR. However, existing methods between the retrieval and pre-training stages lead to significant redundancy in the pseudo-word tokens. In this paper, we propose a novel denoising image-to-word mapping approach, named Denoise-I2W, for m"},"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":"2410.17393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-22T20:01:00Z","cross_cats_sorted":[],"title_canon_sha256":"ae5381447f2ad17319b16e7720fb7be0717aafbe8dea18669c0624f6f42e1997","abstract_canon_sha256":"efa5dccad273333312a07b51bab2716874f71e6f59d1eb8f5fef28a5d3b12d4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:21.496696Z","signature_b64":"R5m2uGnpAbIWa46asgivFW3+9dgMkkT/ENT7zpNtnJ/fRB8LLkrPRYQZz6LHXs3xXpiMpgcCfBqfGqpe1rZiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1caf99598a1eea25d0f700f3fdcfbbf63ce8f18c2c13b6b7a72d10e12172b3e","last_reissued_at":"2026-07-05T09:24:21.496199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:21.496199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Denoise-I2W: Mapping Images to Denoising Words for Accurate Zero-Shot Composed Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Xiong, Gaopeng Gou, Jiamin Zhuang, Jing Yu, Keke Gai, Qi Wu, Yuanmin Tang","submitted_at":"2024-10-22T20:01:00Z","abstract_excerpt":"Zero-Shot Composed Image Retrieval (ZS-CIR) supports diverse tasks with a broad range of visual content manipulation intentions that can be related to domain, scene, object, and attribute. A key challenge for ZS-CIR is to accurately map image representation to a pseudo-word token that captures the manipulation intention relevant image information for generalized CIR. However, existing methods between the retrieval and pre-training stages lead to significant redundancy in the pseudo-word tokens. In this paper, we propose a novel denoising image-to-word mapping approach, named Denoise-I2W, for m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17393","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/2410.17393/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":"2410.17393","created_at":"2026-07-05T09:24:21.496257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17393v1","created_at":"2026-07-05T09:24:21.496257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17393","created_at":"2026-07-05T09:24:21.496257+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHFPTFMYUHXK","created_at":"2026-07-05T09:24:21.496257+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHFPTFMYUHXKEXIP","created_at":"2026-07-05T09:24:21.496257+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHFPTFMY","created_at":"2026-07-05T09:24:21.496257+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/UHFPTFMYUHXKEXIPOAHT7XH3X5","json":"https://pith.science/pith/UHFPTFMYUHXKEXIPOAHT7XH3X5.json","graph_json":"https://pith.science/api/pith-number/UHFPTFMYUHXKEXIPOAHT7XH3X5/graph.json","events_json":"https://pith.science/api/pith-number/UHFPTFMYUHXKEXIPOAHT7XH3X5/events.json","paper":"https://pith.science/paper/UHFPTFMY"},"agent_actions":{"view_html":"https://pith.science/pith/UHFPTFMYUHXKEXIPOAHT7XH3X5","download_json":"https://pith.science/pith/UHFPTFMYUHXKEXIPOAHT7XH3X5.json","view_paper":"https://pith.science/paper/UHFPTFMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17393&json=true","fetch_graph":"https://pith.science/api/pith-number/UHFPTFMYUHXKEXIPOAHT7XH3X5/graph.json","fetch_events":"https://pith.science/api/pith-number/UHFPTFMYUHXKEXIPOAHT7XH3X5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHFPTFMYUHXKEXIPOAHT7XH3X5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHFPTFMYUHXKEXIPOAHT7XH3X5/action/storage_attestation","attest_author":"https://pith.science/pith/UHFPTFMYUHXKEXIPOAHT7XH3X5/action/author_attestation","sign_citation":"https://pith.science/pith/UHFPTFMYUHXKEXIPOAHT7XH3X5/action/citation_signature","submit_replication":"https://pith.science/pith/UHFPTFMYUHXKEXIPOAHT7XH3X5/action/replication_record"}},"created_at":"2026-07-05T09:24:21.496257+00:00","updated_at":"2026-07-05T09:24:21.496257+00:00"}