{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:YLICT6G5SQJHRVYFD6BDBEVRJ5","short_pith_number":"pith:YLICT6G5","schema_version":"1.0","canonical_sha256":"c2d029f8dd941278d7051f823092b14f56c3478ad9108b3800359ded1115bcb1","source":{"kind":"arxiv","id":"1407.3867","version":1},"attestation_state":"computed","paper":{"title":"Part-based R-CNNs for Fine-grained Category Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jeff Donahue, Ning Zhang, Ross Girshick, Trevor Darrell","submitted_at":"2014-07-15T02:32:16Z","abstract_excerpt":"Semantic part localization can facilitate fine-grained categorization by explicitly isolating subtle appearance differences associated with specific object parts. Methods for pose-normalized representations have been proposed, but generally presume bounding box annotations at test time due to the difficulty of object detection. We propose a model for fine-grained categorization that overcomes these limitations by leveraging deep convolutional features computed on bottom-up region proposals. Our method learns whole-object and part detectors, enforces learned geometric constraints between them, "},"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":"1407.3867","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-07-15T02:32:16Z","cross_cats_sorted":[],"title_canon_sha256":"1b3987f5e21a6d925bc2f17fb2e203ccdb2af55e22a0aa8b8cb9edee6637b355","abstract_canon_sha256":"7fc11147c7f1c665f5933051044186a8d55becc05389182f76ed8aa19ecb1e82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:47:32.418300Z","signature_b64":"7xodxjhKG1GPv/6mfcCzqpZBaYx40yr9uPscCRtfqmKBUEmbC/bW6o3H1f9kxhqoSWIK6Dq5MxUdYpLpXgSaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2d029f8dd941278d7051f823092b14f56c3478ad9108b3800359ded1115bcb1","last_reissued_at":"2026-05-18T02:47:32.417716Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:47:32.417716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Part-based R-CNNs for Fine-grained Category Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jeff Donahue, Ning Zhang, Ross Girshick, Trevor Darrell","submitted_at":"2014-07-15T02:32:16Z","abstract_excerpt":"Semantic part localization can facilitate fine-grained categorization by explicitly isolating subtle appearance differences associated with specific object parts. Methods for pose-normalized representations have been proposed, but generally presume bounding box annotations at test time due to the difficulty of object detection. We propose a model for fine-grained categorization that overcomes these limitations by leveraging deep convolutional features computed on bottom-up region proposals. Our method learns whole-object and part detectors, enforces learned geometric constraints between them, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.3867","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":""},"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":"1407.3867","created_at":"2026-05-18T02:47:32.417809+00:00"},{"alias_kind":"arxiv_version","alias_value":"1407.3867v1","created_at":"2026-05-18T02:47:32.417809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.3867","created_at":"2026-05-18T02:47:32.417809+00:00"},{"alias_kind":"pith_short_12","alias_value":"YLICT6G5SQJH","created_at":"2026-05-18T12:28:57.508820+00:00"},{"alias_kind":"pith_short_16","alias_value":"YLICT6G5SQJHRVYF","created_at":"2026-05-18T12:28:57.508820+00:00"},{"alias_kind":"pith_short_8","alias_value":"YLICT6G5","created_at":"2026-05-18T12:28:57.508820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.18700","citing_title":"A Large-Scale Study on the Accuracy vs Cost Trade-offs of Training and Evaluation Settings in Fine-Grained Image Recognition","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YLICT6G5SQJHRVYFD6BDBEVRJ5","json":"https://pith.science/pith/YLICT6G5SQJHRVYFD6BDBEVRJ5.json","graph_json":"https://pith.science/api/pith-number/YLICT6G5SQJHRVYFD6BDBEVRJ5/graph.json","events_json":"https://pith.science/api/pith-number/YLICT6G5SQJHRVYFD6BDBEVRJ5/events.json","paper":"https://pith.science/paper/YLICT6G5"},"agent_actions":{"view_html":"https://pith.science/pith/YLICT6G5SQJHRVYFD6BDBEVRJ5","download_json":"https://pith.science/pith/YLICT6G5SQJHRVYFD6BDBEVRJ5.json","view_paper":"https://pith.science/paper/YLICT6G5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1407.3867&json=true","fetch_graph":"https://pith.science/api/pith-number/YLICT6G5SQJHRVYFD6BDBEVRJ5/graph.json","fetch_events":"https://pith.science/api/pith-number/YLICT6G5SQJHRVYFD6BDBEVRJ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YLICT6G5SQJHRVYFD6BDBEVRJ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YLICT6G5SQJHRVYFD6BDBEVRJ5/action/storage_attestation","attest_author":"https://pith.science/pith/YLICT6G5SQJHRVYFD6BDBEVRJ5/action/author_attestation","sign_citation":"https://pith.science/pith/YLICT6G5SQJHRVYFD6BDBEVRJ5/action/citation_signature","submit_replication":"https://pith.science/pith/YLICT6G5SQJHRVYFD6BDBEVRJ5/action/replication_record"}},"created_at":"2026-05-18T02:47:32.417809+00:00","updated_at":"2026-05-18T02:47:32.417809+00:00"}