{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F3XHCNJIK6XSI6IFKFH4MFRV2N","short_pith_number":"pith:F3XHCNJI","schema_version":"1.0","canonical_sha256":"2eee71352857af247905514fc61635d35963fe06a5b2d5806d0d37252a8c6dbe","source":{"kind":"arxiv","id":"2411.08334","version":3},"attestation_state":"computed","paper":{"title":"MIRe: Enhancing Multimodal Queries Representation via Fusion-Free Modality Interaction for Multimodal Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Ho-Joong Kim, Seong-Whan Lee, Yeong-Joon Ju","submitted_at":"2024-11-13T04:32:58Z","abstract_excerpt":"Recent multimodal retrieval methods have endowed text-based retrievers with multimodal capabilities by utilizing pre-training strategies for visual-text alignment. They often directly fuse the two modalities for cross-reference during the alignment to understand multimodal queries. However, existing methods often overlook crucial visual information due to a text-dominant issue, which overly depends on text-driven signals. In this paper, we introduce MIRe, a retrieval framework that achieves modality interaction without fusing textual features during the alignment. Our method allows the textual"},"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":"2411.08334","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-13T04:32:58Z","cross_cats_sorted":["cs.AI","cs.IR","cs.MM"],"title_canon_sha256":"89114a2a727d904e8a3b3bfccf93c914c016fc328c651b22d9610477bc080b12","abstract_canon_sha256":"30b424d5fd294526eb91e975735463974194751367f9615fdf7eebbb763b7ac2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:25.011888Z","signature_b64":"GsJccMPGkT09H5l+2s+tzN34+rqrT8xXiq07TGNx0SjZBaaPHgkPyFyvg6GCjYTDYyOuoCRy9Gvd6uXK5OhHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2eee71352857af247905514fc61635d35963fe06a5b2d5806d0d37252a8c6dbe","last_reissued_at":"2026-07-05T11:06:25.011384Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:25.011384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIRe: Enhancing Multimodal Queries Representation via Fusion-Free Modality Interaction for Multimodal Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Ho-Joong Kim, Seong-Whan Lee, Yeong-Joon Ju","submitted_at":"2024-11-13T04:32:58Z","abstract_excerpt":"Recent multimodal retrieval methods have endowed text-based retrievers with multimodal capabilities by utilizing pre-training strategies for visual-text alignment. They often directly fuse the two modalities for cross-reference during the alignment to understand multimodal queries. However, existing methods often overlook crucial visual information due to a text-dominant issue, which overly depends on text-driven signals. In this paper, we introduce MIRe, a retrieval framework that achieves modality interaction without fusing textual features during the alignment. Our method allows the textual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08334","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/2411.08334/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":"2411.08334","created_at":"2026-07-05T11:06:25.011446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.08334v3","created_at":"2026-07-05T11:06:25.011446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08334","created_at":"2026-07-05T11:06:25.011446+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3XHCNJIK6XS","created_at":"2026-07-05T11:06:25.011446+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3XHCNJIK6XSI6IF","created_at":"2026-07-05T11:06:25.011446+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3XHCNJI","created_at":"2026-07-05T11:06:25.011446+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/F3XHCNJIK6XSI6IFKFH4MFRV2N","json":"https://pith.science/pith/F3XHCNJIK6XSI6IFKFH4MFRV2N.json","graph_json":"https://pith.science/api/pith-number/F3XHCNJIK6XSI6IFKFH4MFRV2N/graph.json","events_json":"https://pith.science/api/pith-number/F3XHCNJIK6XSI6IFKFH4MFRV2N/events.json","paper":"https://pith.science/paper/F3XHCNJI"},"agent_actions":{"view_html":"https://pith.science/pith/F3XHCNJIK6XSI6IFKFH4MFRV2N","download_json":"https://pith.science/pith/F3XHCNJIK6XSI6IFKFH4MFRV2N.json","view_paper":"https://pith.science/paper/F3XHCNJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.08334&json=true","fetch_graph":"https://pith.science/api/pith-number/F3XHCNJIK6XSI6IFKFH4MFRV2N/graph.json","fetch_events":"https://pith.science/api/pith-number/F3XHCNJIK6XSI6IFKFH4MFRV2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3XHCNJIK6XSI6IFKFH4MFRV2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3XHCNJIK6XSI6IFKFH4MFRV2N/action/storage_attestation","attest_author":"https://pith.science/pith/F3XHCNJIK6XSI6IFKFH4MFRV2N/action/author_attestation","sign_citation":"https://pith.science/pith/F3XHCNJIK6XSI6IFKFH4MFRV2N/action/citation_signature","submit_replication":"https://pith.science/pith/F3XHCNJIK6XSI6IFKFH4MFRV2N/action/replication_record"}},"created_at":"2026-07-05T11:06:25.011446+00:00","updated_at":"2026-07-05T11:06:25.011446+00:00"}