{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:RRV2JP647A7V4KNBGAUOPQECA2","short_pith_number":"pith:RRV2JP64","schema_version":"1.0","canonical_sha256":"8c6ba4bfdcf83f5e29a13028e7c082069e1334afbcfa40519695114d25655b77","source":{"kind":"arxiv","id":"1611.09932","version":3},"attestation_state":"computed","paper":{"title":"Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Larry S. Davis, Vlad I. Morariu, Yaming Wang","submitted_at":"2016-11-29T23:01:59Z","abstract_excerpt":"Compared to earlier multistage frameworks using CNN features, recent end-to-end deep approaches for fine-grained recognition essentially enhance the mid-level learning capability of CNNs. Previous approaches achieve this by introducing an auxiliary network to infuse localization information into the main classification network, or a sophisticated feature encoding method to capture higher order feature statistics. We show that mid-level representation learning can be enhanced within the CNN framework, by learning a bank of convolutional filters that capture class-specific discriminative patches"},"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":"1611.09932","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-29T23:01:59Z","cross_cats_sorted":[],"title_canon_sha256":"07c5592ccad065d0e1272ad5f8f5d01476250672e2f655710183a79dbe7d7c25","abstract_canon_sha256":"a1fbcda98176c843c66a7454ecc93b1fbf9f5792b7e5e43a88c9feb8f57818f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:38.008601Z","signature_b64":"VmjF7Z3JSSHRGNd+WwL5RqF0XDIrv9mvyXMI9EUkKIELP+0jWx+p/81/a+glohzJp4IVzV4uA5OXPdmQcPV4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c6ba4bfdcf83f5e29a13028e7c082069e1334afbcfa40519695114d25655b77","last_reissued_at":"2026-05-18T00:13:38.008081Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:38.008081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Larry S. Davis, Vlad I. Morariu, Yaming Wang","submitted_at":"2016-11-29T23:01:59Z","abstract_excerpt":"Compared to earlier multistage frameworks using CNN features, recent end-to-end deep approaches for fine-grained recognition essentially enhance the mid-level learning capability of CNNs. Previous approaches achieve this by introducing an auxiliary network to infuse localization information into the main classification network, or a sophisticated feature encoding method to capture higher order feature statistics. We show that mid-level representation learning can be enhanced within the CNN framework, by learning a bank of convolutional filters that capture class-specific discriminative patches"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.09932","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":""},"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":"1611.09932","created_at":"2026-05-18T00:13:38.008152+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.09932v3","created_at":"2026-05-18T00:13:38.008152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.09932","created_at":"2026-05-18T00:13:38.008152+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRV2JP647A7V","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRV2JP647A7V4KNB","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRV2JP64","created_at":"2026-05-18T12:30:41.710351+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/RRV2JP647A7V4KNBGAUOPQECA2","json":"https://pith.science/pith/RRV2JP647A7V4KNBGAUOPQECA2.json","graph_json":"https://pith.science/api/pith-number/RRV2JP647A7V4KNBGAUOPQECA2/graph.json","events_json":"https://pith.science/api/pith-number/RRV2JP647A7V4KNBGAUOPQECA2/events.json","paper":"https://pith.science/paper/RRV2JP64"},"agent_actions":{"view_html":"https://pith.science/pith/RRV2JP647A7V4KNBGAUOPQECA2","download_json":"https://pith.science/pith/RRV2JP647A7V4KNBGAUOPQECA2.json","view_paper":"https://pith.science/paper/RRV2JP64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.09932&json=true","fetch_graph":"https://pith.science/api/pith-number/RRV2JP647A7V4KNBGAUOPQECA2/graph.json","fetch_events":"https://pith.science/api/pith-number/RRV2JP647A7V4KNBGAUOPQECA2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRV2JP647A7V4KNBGAUOPQECA2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRV2JP647A7V4KNBGAUOPQECA2/action/storage_attestation","attest_author":"https://pith.science/pith/RRV2JP647A7V4KNBGAUOPQECA2/action/author_attestation","sign_citation":"https://pith.science/pith/RRV2JP647A7V4KNBGAUOPQECA2/action/citation_signature","submit_replication":"https://pith.science/pith/RRV2JP647A7V4KNBGAUOPQECA2/action/replication_record"}},"created_at":"2026-05-18T00:13:38.008152+00:00","updated_at":"2026-05-18T00:13:38.008152+00:00"}