{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:5ABY6OB6TDHUC44GV42X36OSV7","short_pith_number":"pith:5ABY6OB6","schema_version":"1.0","canonical_sha256":"e8038f383e98cf417386af357df9d2afd12e5814103246041dd399e7d871a3ef","source":{"kind":"arxiv","id":"1707.00809","version":2},"attestation_state":"computed","paper":{"title":"Selective Deep Convolutional Features for Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dang-Khoa Le Tan, Ngai-Man Cheung, Thanh-Toan Do, Tuan Hoang","submitted_at":"2017-07-04T03:38:15Z","abstract_excerpt":"Convolutional Neural Network (CNN) is a very powerful approach to extract discriminative local descriptors for effective image search. Recent work adopts fine-tuned strategies to further improve the discriminative power of the descriptors. Taking a different approach, in this paper, we propose a novel framework to achieve competitive retrieval performance. Firstly, we propose various masking schemes, namely SIFT-mask, SUM-mask, and MAX-mask, to select a representative subset of local convolutional features and remove a large number of redundant features. We demonstrate that this can effectivel"},"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":"1707.00809","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-04T03:38:15Z","cross_cats_sorted":[],"title_canon_sha256":"af51666006affb9b4653fcc51a787b93cb68be7207880b419b7386bba71c82e0","abstract_canon_sha256":"e4193c0c37239da818afbe83fcdb542bf99a016832ee0d817337e1318319a26a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:38.905459Z","signature_b64":"B2PNj+LvsIQ/EHzg6rjVV26uqaWP2Pr1XgaLcEfV/hIdSbvQ+3jA7zGWFyB9bYUkWpdsTLMK8dtGTzhnE11dCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8038f383e98cf417386af357df9d2afd12e5814103246041dd399e7d871a3ef","last_reissued_at":"2026-05-18T00:29:38.905044Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:38.905044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Selective Deep Convolutional Features for Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dang-Khoa Le Tan, Ngai-Man Cheung, Thanh-Toan Do, Tuan Hoang","submitted_at":"2017-07-04T03:38:15Z","abstract_excerpt":"Convolutional Neural Network (CNN) is a very powerful approach to extract discriminative local descriptors for effective image search. Recent work adopts fine-tuned strategies to further improve the discriminative power of the descriptors. Taking a different approach, in this paper, we propose a novel framework to achieve competitive retrieval performance. Firstly, we propose various masking schemes, namely SIFT-mask, SUM-mask, and MAX-mask, to select a representative subset of local convolutional features and remove a large number of redundant features. We demonstrate that this can effectivel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.00809","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":"1707.00809","created_at":"2026-05-18T00:29:38.905107+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.00809v2","created_at":"2026-05-18T00:29:38.905107+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.00809","created_at":"2026-05-18T00:29:38.905107+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ABY6OB6TDHU","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ABY6OB6TDHUC44G","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ABY6OB6","created_at":"2026-05-18T12:31:00.734936+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/5ABY6OB6TDHUC44GV42X36OSV7","json":"https://pith.science/pith/5ABY6OB6TDHUC44GV42X36OSV7.json","graph_json":"https://pith.science/api/pith-number/5ABY6OB6TDHUC44GV42X36OSV7/graph.json","events_json":"https://pith.science/api/pith-number/5ABY6OB6TDHUC44GV42X36OSV7/events.json","paper":"https://pith.science/paper/5ABY6OB6"},"agent_actions":{"view_html":"https://pith.science/pith/5ABY6OB6TDHUC44GV42X36OSV7","download_json":"https://pith.science/pith/5ABY6OB6TDHUC44GV42X36OSV7.json","view_paper":"https://pith.science/paper/5ABY6OB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.00809&json=true","fetch_graph":"https://pith.science/api/pith-number/5ABY6OB6TDHUC44GV42X36OSV7/graph.json","fetch_events":"https://pith.science/api/pith-number/5ABY6OB6TDHUC44GV42X36OSV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ABY6OB6TDHUC44GV42X36OSV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ABY6OB6TDHUC44GV42X36OSV7/action/storage_attestation","attest_author":"https://pith.science/pith/5ABY6OB6TDHUC44GV42X36OSV7/action/author_attestation","sign_citation":"https://pith.science/pith/5ABY6OB6TDHUC44GV42X36OSV7/action/citation_signature","submit_replication":"https://pith.science/pith/5ABY6OB6TDHUC44GV42X36OSV7/action/replication_record"}},"created_at":"2026-05-18T00:29:38.905107+00:00","updated_at":"2026-05-18T00:29:38.905107+00:00"}