{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:VXASWAV7UIOBWYS6RWBCW2HNZM","short_pith_number":"pith:VXASWAV7","schema_version":"1.0","canonical_sha256":"adc12b02bfa21c1b625e8d822b68edcb0be7d296db6e3c32a183d95c6bf58ef8","source":{"kind":"arxiv","id":"1509.02470","version":1},"attestation_state":"computed","paper":{"title":"Deep Attributes from Context-Aware Regional Neural Codes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Jianguo Li, Jianwei Luo, Jun Wang, Yurong Chen, Zhiguo Jiang","submitted_at":"2015-09-08T17:53:54Z","abstract_excerpt":"Recently, many researches employ middle-layer output of convolutional neural network models (CNN) as features for different visual recognition tasks. Although promising results have been achieved in some empirical studies, such type of representations still suffer from the well-known issue of semantic gap. This paper proposes so-called deep attribute framework to alleviate this issue from three aspects. First, we introduce object region proposals as intermedia to represent target images, and extract features from region proposals. Second, we study aggregating features from different CNN layers"},"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":"1509.02470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-09-08T17:53:54Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"ccab5375d6ff226b48543a61f5274d7693eb9af341b55d26be85d423208a71ac","abstract_canon_sha256":"9c1d31794b2ae7c9f65b2f7cef37d509e8280449d051450e195dd187ad4d5192"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:33:40.836434Z","signature_b64":"4HtuQZ8jsGS93DRQSfAKGC+v5Rgrx5Yso+Ntdwg4xm/a1C/ajD3TcMyUvn9FNI4EXzA1V3Sc5WDo5/JWgd4GDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adc12b02bfa21c1b625e8d822b68edcb0be7d296db6e3c32a183d95c6bf58ef8","last_reissued_at":"2026-05-18T01:33:40.836011Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:33:40.836011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Attributes from Context-Aware Regional Neural Codes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Jianguo Li, Jianwei Luo, Jun Wang, Yurong Chen, Zhiguo Jiang","submitted_at":"2015-09-08T17:53:54Z","abstract_excerpt":"Recently, many researches employ middle-layer output of convolutional neural network models (CNN) as features for different visual recognition tasks. Although promising results have been achieved in some empirical studies, such type of representations still suffer from the well-known issue of semantic gap. This paper proposes so-called deep attribute framework to alleviate this issue from three aspects. First, we introduce object region proposals as intermedia to represent target images, and extract features from region proposals. Second, we study aggregating features from different CNN layers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.02470","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":"1509.02470","created_at":"2026-05-18T01:33:40.836077+00:00"},{"alias_kind":"arxiv_version","alias_value":"1509.02470v1","created_at":"2026-05-18T01:33:40.836077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.02470","created_at":"2026-05-18T01:33:40.836077+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXASWAV7UIOB","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXASWAV7UIOBWYS6","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXASWAV7","created_at":"2026-05-18T12:29:47.479230+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/VXASWAV7UIOBWYS6RWBCW2HNZM","json":"https://pith.science/pith/VXASWAV7UIOBWYS6RWBCW2HNZM.json","graph_json":"https://pith.science/api/pith-number/VXASWAV7UIOBWYS6RWBCW2HNZM/graph.json","events_json":"https://pith.science/api/pith-number/VXASWAV7UIOBWYS6RWBCW2HNZM/events.json","paper":"https://pith.science/paper/VXASWAV7"},"agent_actions":{"view_html":"https://pith.science/pith/VXASWAV7UIOBWYS6RWBCW2HNZM","download_json":"https://pith.science/pith/VXASWAV7UIOBWYS6RWBCW2HNZM.json","view_paper":"https://pith.science/paper/VXASWAV7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1509.02470&json=true","fetch_graph":"https://pith.science/api/pith-number/VXASWAV7UIOBWYS6RWBCW2HNZM/graph.json","fetch_events":"https://pith.science/api/pith-number/VXASWAV7UIOBWYS6RWBCW2HNZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXASWAV7UIOBWYS6RWBCW2HNZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXASWAV7UIOBWYS6RWBCW2HNZM/action/storage_attestation","attest_author":"https://pith.science/pith/VXASWAV7UIOBWYS6RWBCW2HNZM/action/author_attestation","sign_citation":"https://pith.science/pith/VXASWAV7UIOBWYS6RWBCW2HNZM/action/citation_signature","submit_replication":"https://pith.science/pith/VXASWAV7UIOBWYS6RWBCW2HNZM/action/replication_record"}},"created_at":"2026-05-18T01:33:40.836077+00:00","updated_at":"2026-05-18T01:33:40.836077+00:00"}