{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:A4JCT5U4ROW7UXBJNIILADOZLZ","short_pith_number":"pith:A4JCT5U4","schema_version":"1.0","canonical_sha256":"071229f69c8badfa5c296a10b00dd95e4e28238138e18c2ab3ceb190eb70d5cf","source":{"kind":"arxiv","id":"1702.08692","version":2},"attestation_state":"computed","paper":{"title":"Cascade one-vs-rest detection network for fine-grained recognition without part annotations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hua Zhang, Junyu Dong, Kin-man Lam, Long Chen, Muwei Jian, ShengKe Wang, Xiaochun Cao","submitted_at":"2017-02-28T08:45:15Z","abstract_excerpt":"Fine-grained recognition is a challenging task due to the small intra-category variances. Most of top-performing fine-grained recognition methods leverage parts of objects for better performance. Therefore, part annotations which are extremely computationally expensive are required. In this paper, we propose a novel cascaded deep CNN detection framework for fine-grained recognition which is trained to detect the whole object without considering parts. Nevertheless, most of current top-performing detection networks use the N+1 class (N object categories plus background) softmax loss, and the ba"},"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":"1702.08692","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-28T08:45:15Z","cross_cats_sorted":[],"title_canon_sha256":"918ad325b1cfd396e9579a0a47129a3ccddf31f10ac7e60b61c3d5d273c658ff","abstract_canon_sha256":"e4b189c46972cba480f156bdc9f1c4e84b3281c80215a96c55f28504b95d7339"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:51.276916Z","signature_b64":"1w+2ah385IdDOyichxDk66PGZBmsC4B+QC19BmjYNMQKEAbEuHJWtZgpRMZHT8+QISIKBObulECyyDOdWeJ7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"071229f69c8badfa5c296a10b00dd95e4e28238138e18c2ab3ceb190eb70d5cf","last_reissued_at":"2026-05-18T00:36:51.276443Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:51.276443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cascade one-vs-rest detection network for fine-grained recognition without part annotations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hua Zhang, Junyu Dong, Kin-man Lam, Long Chen, Muwei Jian, ShengKe Wang, Xiaochun Cao","submitted_at":"2017-02-28T08:45:15Z","abstract_excerpt":"Fine-grained recognition is a challenging task due to the small intra-category variances. Most of top-performing fine-grained recognition methods leverage parts of objects for better performance. Therefore, part annotations which are extremely computationally expensive are required. In this paper, we propose a novel cascaded deep CNN detection framework for fine-grained recognition which is trained to detect the whole object without considering parts. Nevertheless, most of current top-performing detection networks use the N+1 class (N object categories plus background) softmax loss, and the ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08692","kind":"arxiv","version":2},"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":"1702.08692","created_at":"2026-05-18T00:36:51.276514+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.08692v2","created_at":"2026-05-18T00:36:51.276514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08692","created_at":"2026-05-18T00:36:51.276514+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4JCT5U4ROW7","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4JCT5U4ROW7UXBJ","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4JCT5U4","created_at":"2026-05-18T12:31:05.417338+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/A4JCT5U4ROW7UXBJNIILADOZLZ","json":"https://pith.science/pith/A4JCT5U4ROW7UXBJNIILADOZLZ.json","graph_json":"https://pith.science/api/pith-number/A4JCT5U4ROW7UXBJNIILADOZLZ/graph.json","events_json":"https://pith.science/api/pith-number/A4JCT5U4ROW7UXBJNIILADOZLZ/events.json","paper":"https://pith.science/paper/A4JCT5U4"},"agent_actions":{"view_html":"https://pith.science/pith/A4JCT5U4ROW7UXBJNIILADOZLZ","download_json":"https://pith.science/pith/A4JCT5U4ROW7UXBJNIILADOZLZ.json","view_paper":"https://pith.science/paper/A4JCT5U4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.08692&json=true","fetch_graph":"https://pith.science/api/pith-number/A4JCT5U4ROW7UXBJNIILADOZLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/A4JCT5U4ROW7UXBJNIILADOZLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4JCT5U4ROW7UXBJNIILADOZLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4JCT5U4ROW7UXBJNIILADOZLZ/action/storage_attestation","attest_author":"https://pith.science/pith/A4JCT5U4ROW7UXBJNIILADOZLZ/action/author_attestation","sign_citation":"https://pith.science/pith/A4JCT5U4ROW7UXBJNIILADOZLZ/action/citation_signature","submit_replication":"https://pith.science/pith/A4JCT5U4ROW7UXBJNIILADOZLZ/action/replication_record"}},"created_at":"2026-05-18T00:36:51.276514+00:00","updated_at":"2026-05-18T00:36:51.276514+00:00"}