{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EZGGK3Q5MAT7BHJZRX6RELEGJ3","short_pith_number":"pith:EZGGK3Q5","schema_version":"1.0","canonical_sha256":"264c656e1d6027f09d398dfd122c864ed61c57e0699c38eda83835d626f3a694","source":{"kind":"arxiv","id":"2504.16691","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Vision Transformer for Large-Scale Fine-Grained Image Retrieval","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Hao Tang, Xin Jiang, Yonghua Pan, Zechao Li","submitted_at":"2025-04-23T13:23:56Z","abstract_excerpt":"Large-scale fine-grained image retrieval (FGIR) aims to retrieve images belonging to the same subcategory as a given query by capturing subtle differences in a large-scale setting. Recently, Vision Transformers (ViT) have been employed in FGIR due to their powerful self-attention mechanism for modeling long-range dependencies. However, most Transformer-based methods focus primarily on leveraging self-attention to distinguish fine-grained details, while overlooking the high computational complexity and redundant dependencies inherent to these models, limiting their scalability and effectiveness"},"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":"2504.16691","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.MM","submitted_at":"2025-04-23T13:23:56Z","cross_cats_sorted":[],"title_canon_sha256":"a1c2004b9537a8d3c97f23ac3233d11c78041c4ecb27ffc54cfc753d079ba6b0","abstract_canon_sha256":"4b77ec466048bfc70b71177c06e9bcf7e5b46194ce0749d00ec0b03c48788465"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:03.306449Z","signature_b64":"+tvcQfUiBrzevKap6rW7Sc/6QdRf62vDqp3FCtSGbJsJEWwY/F0GaM4jRKcG1BJQ7LKteYcPc0+R1O9TNZfsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"264c656e1d6027f09d398dfd122c864ed61c57e0699c38eda83835d626f3a694","last_reissued_at":"2026-07-05T10:53:03.305952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:03.305952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Vision Transformer for Large-Scale Fine-Grained Image Retrieval","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Hao Tang, Xin Jiang, Yonghua Pan, Zechao Li","submitted_at":"2025-04-23T13:23:56Z","abstract_excerpt":"Large-scale fine-grained image retrieval (FGIR) aims to retrieve images belonging to the same subcategory as a given query by capturing subtle differences in a large-scale setting. Recently, Vision Transformers (ViT) have been employed in FGIR due to their powerful self-attention mechanism for modeling long-range dependencies. However, most Transformer-based methods focus primarily on leveraging self-attention to distinguish fine-grained details, while overlooking the high computational complexity and redundant dependencies inherent to these models, limiting their scalability and effectiveness"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16691","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/2504.16691/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":"2504.16691","created_at":"2026-07-05T10:53:03.306010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16691v1","created_at":"2026-07-05T10:53:03.306010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16691","created_at":"2026-07-05T10:53:03.306010+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZGGK3Q5MAT7","created_at":"2026-07-05T10:53:03.306010+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZGGK3Q5MAT7BHJZ","created_at":"2026-07-05T10:53:03.306010+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZGGK3Q5","created_at":"2026-07-05T10:53:03.306010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18885","citing_title":"LARE: Low-Attention Region Encoding for Text-Image Retrieval","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZGGK3Q5MAT7BHJZRX6RELEGJ3","json":"https://pith.science/pith/EZGGK3Q5MAT7BHJZRX6RELEGJ3.json","graph_json":"https://pith.science/api/pith-number/EZGGK3Q5MAT7BHJZRX6RELEGJ3/graph.json","events_json":"https://pith.science/api/pith-number/EZGGK3Q5MAT7BHJZRX6RELEGJ3/events.json","paper":"https://pith.science/paper/EZGGK3Q5"},"agent_actions":{"view_html":"https://pith.science/pith/EZGGK3Q5MAT7BHJZRX6RELEGJ3","download_json":"https://pith.science/pith/EZGGK3Q5MAT7BHJZRX6RELEGJ3.json","view_paper":"https://pith.science/paper/EZGGK3Q5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16691&json=true","fetch_graph":"https://pith.science/api/pith-number/EZGGK3Q5MAT7BHJZRX6RELEGJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/EZGGK3Q5MAT7BHJZRX6RELEGJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZGGK3Q5MAT7BHJZRX6RELEGJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZGGK3Q5MAT7BHJZRX6RELEGJ3/action/storage_attestation","attest_author":"https://pith.science/pith/EZGGK3Q5MAT7BHJZRX6RELEGJ3/action/author_attestation","sign_citation":"https://pith.science/pith/EZGGK3Q5MAT7BHJZRX6RELEGJ3/action/citation_signature","submit_replication":"https://pith.science/pith/EZGGK3Q5MAT7BHJZRX6RELEGJ3/action/replication_record"}},"created_at":"2026-07-05T10:53:03.306010+00:00","updated_at":"2026-07-05T10:53:03.306010+00:00"}