{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:6HOBFSMCE55AALEXBD7YYP2VFW","short_pith_number":"pith:6HOBFSMC","schema_version":"1.0","canonical_sha256":"f1dc12c982277a002c9708ff8c3f552d8c975bfc380a418ea4614fd0e898b39e","source":{"kind":"arxiv","id":"1603.06765","version":4},"attestation_state":"computed","paper":{"title":"Fully Convolutional Attention Networks for Fine-Grained Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhou, Jiang Wang, Tian Xia, Xiao Liu, Yi Yang, Yuanqing Lin","submitted_at":"2016-03-22T12:45:20Z","abstract_excerpt":"Fine-grained recognition is challenging due to its subtle local inter-class differences versus large intra-class variations such as poses. A key to address this problem is to localize discriminative parts to extract pose-invariant features. However, ground-truth part annotations can be expensive to acquire. Moreover, it is hard to define parts for many fine-grained classes. This work introduces Fully Convolutional Attention Networks (FCANs), a reinforcement learning framework to optimally glimpse local discriminative regions adaptive to different fine-grained domains. Compared to previous meth"},"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":"1603.06765","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-22T12:45:20Z","cross_cats_sorted":[],"title_canon_sha256":"43148609ca9b00735d1f7fda29996a5cfe0d5df1a6523c61b47e885897656732","abstract_canon_sha256":"12afe5201701dd7f974883b58d9b21a621fb512c61738b97621a5e758c3f633e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:20.124078Z","signature_b64":"SwA/75hSPqR4Dw+o5tqn3FQUvKnPWAGElxocBNrF261zjseIi4ObUAZ7AuMxmx9daWBrmfWjeKc9aMNEuIcSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1dc12c982277a002c9708ff8c3f552d8c975bfc380a418ea4614fd0e898b39e","last_reissued_at":"2026-05-18T00:48:20.123400Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:20.123400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fully Convolutional Attention Networks for Fine-Grained Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhou, Jiang Wang, Tian Xia, Xiao Liu, Yi Yang, Yuanqing Lin","submitted_at":"2016-03-22T12:45:20Z","abstract_excerpt":"Fine-grained recognition is challenging due to its subtle local inter-class differences versus large intra-class variations such as poses. A key to address this problem is to localize discriminative parts to extract pose-invariant features. However, ground-truth part annotations can be expensive to acquire. Moreover, it is hard to define parts for many fine-grained classes. This work introduces Fully Convolutional Attention Networks (FCANs), a reinforcement learning framework to optimally glimpse local discriminative regions adaptive to different fine-grained domains. Compared to previous meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.06765","kind":"arxiv","version":4},"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":"1603.06765","created_at":"2026-05-18T00:48:20.123504+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.06765v4","created_at":"2026-05-18T00:48:20.123504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.06765","created_at":"2026-05-18T00:48:20.123504+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HOBFSMCE55A","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HOBFSMCE55AALEX","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HOBFSMC","created_at":"2026-05-18T12:30:01.593930+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/6HOBFSMCE55AALEXBD7YYP2VFW","json":"https://pith.science/pith/6HOBFSMCE55AALEXBD7YYP2VFW.json","graph_json":"https://pith.science/api/pith-number/6HOBFSMCE55AALEXBD7YYP2VFW/graph.json","events_json":"https://pith.science/api/pith-number/6HOBFSMCE55AALEXBD7YYP2VFW/events.json","paper":"https://pith.science/paper/6HOBFSMC"},"agent_actions":{"view_html":"https://pith.science/pith/6HOBFSMCE55AALEXBD7YYP2VFW","download_json":"https://pith.science/pith/6HOBFSMCE55AALEXBD7YYP2VFW.json","view_paper":"https://pith.science/paper/6HOBFSMC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.06765&json=true","fetch_graph":"https://pith.science/api/pith-number/6HOBFSMCE55AALEXBD7YYP2VFW/graph.json","fetch_events":"https://pith.science/api/pith-number/6HOBFSMCE55AALEXBD7YYP2VFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HOBFSMCE55AALEXBD7YYP2VFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HOBFSMCE55AALEXBD7YYP2VFW/action/storage_attestation","attest_author":"https://pith.science/pith/6HOBFSMCE55AALEXBD7YYP2VFW/action/author_attestation","sign_citation":"https://pith.science/pith/6HOBFSMCE55AALEXBD7YYP2VFW/action/citation_signature","submit_replication":"https://pith.science/pith/6HOBFSMCE55AALEXBD7YYP2VFW/action/replication_record"}},"created_at":"2026-05-18T00:48:20.123504+00:00","updated_at":"2026-05-18T00:48:20.123504+00:00"}