{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U66WY22BXG6N62ZW5IDYMJCRIB","short_pith_number":"pith:U66WY22B","schema_version":"1.0","canonical_sha256":"a7bd6c6b41b9bcdf6b36ea07862451406e0123d79188765fcc63322cbabfee54","source":{"kind":"arxiv","id":"2503.10324","version":1},"attestation_state":"computed","paper":{"title":"IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Huchuan Lu, Pingping Zhang, Yongfeng Lv, Yuhao Wang","submitted_at":"2025-03-13T13:00:31Z","abstract_excerpt":"Multi-modal object Re-IDentification (ReID) aims to retrieve specific objects by utilizing complementary information from various modalities. However, existing methods focus on fusing heterogeneous visual features, neglecting the potential benefits of text-based semantic information. To address this issue, we first construct three text-enhanced multi-modal object ReID benchmarks. To be specific, we propose a standardized multi-modal caption generation pipeline for structured and concise text annotations with Multi-modal Large Language Models (MLLMs). Besides, current methods often directly agg"},"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":"2503.10324","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T13:00:31Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"92bc38ab90e08c3b0c1db4bf5ec2348d902b66eaa79c696888c6f2cf3b77d2b5","abstract_canon_sha256":"4b4662e6e8f7ef22079cb8378547a42f03e153a7630beb3674b8bd6c9dfbf5fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:42.854463Z","signature_b64":"NUC/4euZm3u5cHVsnUC4DSXmtvUJHZni7Z1C8QyT+AafDszW3B37u8YH9QJp2Y32aBCcUpWiwmxcD+EHh56dAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7bd6c6b41b9bcdf6b36ea07862451406e0123d79188765fcc63322cbabfee54","last_reissued_at":"2026-07-05T10:30:42.853930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:42.853930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Huchuan Lu, Pingping Zhang, Yongfeng Lv, Yuhao Wang","submitted_at":"2025-03-13T13:00:31Z","abstract_excerpt":"Multi-modal object Re-IDentification (ReID) aims to retrieve specific objects by utilizing complementary information from various modalities. However, existing methods focus on fusing heterogeneous visual features, neglecting the potential benefits of text-based semantic information. To address this issue, we first construct three text-enhanced multi-modal object ReID benchmarks. To be specific, we propose a standardized multi-modal caption generation pipeline for structured and concise text annotations with Multi-modal Large Language Models (MLLMs). Besides, current methods often directly agg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10324","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/2503.10324/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":"2503.10324","created_at":"2026-07-05T10:30:42.854001+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10324v1","created_at":"2026-07-05T10:30:42.854001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10324","created_at":"2026-07-05T10:30:42.854001+00:00"},{"alias_kind":"pith_short_12","alias_value":"U66WY22BXG6N","created_at":"2026-07-05T10:30:42.854001+00:00"},{"alias_kind":"pith_short_16","alias_value":"U66WY22BXG6N62ZW","created_at":"2026-07-05T10:30:42.854001+00:00"},{"alias_kind":"pith_short_8","alias_value":"U66WY22B","created_at":"2026-07-05T10:30:42.854001+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.14847","citing_title":"Reliable Multi-Modal Object Re-Identification via Modality-Aware Graph Reasoning","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U66WY22BXG6N62ZW5IDYMJCRIB","json":"https://pith.science/pith/U66WY22BXG6N62ZW5IDYMJCRIB.json","graph_json":"https://pith.science/api/pith-number/U66WY22BXG6N62ZW5IDYMJCRIB/graph.json","events_json":"https://pith.science/api/pith-number/U66WY22BXG6N62ZW5IDYMJCRIB/events.json","paper":"https://pith.science/paper/U66WY22B"},"agent_actions":{"view_html":"https://pith.science/pith/U66WY22BXG6N62ZW5IDYMJCRIB","download_json":"https://pith.science/pith/U66WY22BXG6N62ZW5IDYMJCRIB.json","view_paper":"https://pith.science/paper/U66WY22B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10324&json=true","fetch_graph":"https://pith.science/api/pith-number/U66WY22BXG6N62ZW5IDYMJCRIB/graph.json","fetch_events":"https://pith.science/api/pith-number/U66WY22BXG6N62ZW5IDYMJCRIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U66WY22BXG6N62ZW5IDYMJCRIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U66WY22BXG6N62ZW5IDYMJCRIB/action/storage_attestation","attest_author":"https://pith.science/pith/U66WY22BXG6N62ZW5IDYMJCRIB/action/author_attestation","sign_citation":"https://pith.science/pith/U66WY22BXG6N62ZW5IDYMJCRIB/action/citation_signature","submit_replication":"https://pith.science/pith/U66WY22BXG6N62ZW5IDYMJCRIB/action/replication_record"}},"created_at":"2026-07-05T10:30:42.854001+00:00","updated_at":"2026-07-05T10:30:42.854001+00:00"}