{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:6UJC5EHOIPOXRXJBOME7TMRAMS","short_pith_number":"pith:6UJC5EHO","schema_version":"1.0","canonical_sha256":"f5122e90ee43dd78dd217309f9b2206496e3cabad5de9d1733458f67a1a9d836","source":{"kind":"arxiv","id":"1707.02581","version":1},"attestation_state":"computed","paper":{"title":"Class-Weighted Convolutional Features for Visual Instance Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Albert Jimenez, Jose M. Alvarez, Xavier Giro-i-Nieto","submitted_at":"2017-07-09T13:51:45Z","abstract_excerpt":"Image retrieval in realistic scenarios targets large dynamic datasets of unlabeled images. In these cases, training or fine-tuning a model every time new images are added to the database is neither efficient nor scalable. Convolutional neural networks trained for image classification over large datasets have been proven effective feature extractors for image retrieval. The most successful approaches are based on encoding the activations of convolutional layers, as they convey the image spatial information. In this paper, we go beyond this spatial information and propose a local-aware encoding "},"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":"1707.02581","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-09T13:51:45Z","cross_cats_sorted":["cs.IR","cs.MM"],"title_canon_sha256":"4e231d180da1c621f743872777a29da6486b90411a00e71d3f564463b5fdc7f3","abstract_canon_sha256":"90c092a3b1db28e3948f6a8059b0755035b86d43cc2445987a95c68d9c8c326d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:36.426582Z","signature_b64":"0AQKuUraOvpvBLFeXyc7gGWxi4tR1Q0H9PilVwFSK2f+/Z9ZSLj07TZu1WlpT9hr7aFsJAp82Ff1qGdlRoaLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5122e90ee43dd78dd217309f9b2206496e3cabad5de9d1733458f67a1a9d836","last_reissued_at":"2026-05-18T00:40:36.425957Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:36.425957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Class-Weighted Convolutional Features for Visual Instance Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Albert Jimenez, Jose M. Alvarez, Xavier Giro-i-Nieto","submitted_at":"2017-07-09T13:51:45Z","abstract_excerpt":"Image retrieval in realistic scenarios targets large dynamic datasets of unlabeled images. In these cases, training or fine-tuning a model every time new images are added to the database is neither efficient nor scalable. Convolutional neural networks trained for image classification over large datasets have been proven effective feature extractors for image retrieval. The most successful approaches are based on encoding the activations of convolutional layers, as they convey the image spatial information. In this paper, we go beyond this spatial information and propose a local-aware encoding "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.02581","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":"1707.02581","created_at":"2026-05-18T00:40:36.426056+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.02581v1","created_at":"2026-05-18T00:40:36.426056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.02581","created_at":"2026-05-18T00:40:36.426056+00:00"},{"alias_kind":"pith_short_12","alias_value":"6UJC5EHOIPOX","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"6UJC5EHOIPOXRXJB","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"6UJC5EHO","created_at":"2026-05-18T12:31:03.183658+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/6UJC5EHOIPOXRXJBOME7TMRAMS","json":"https://pith.science/pith/6UJC5EHOIPOXRXJBOME7TMRAMS.json","graph_json":"https://pith.science/api/pith-number/6UJC5EHOIPOXRXJBOME7TMRAMS/graph.json","events_json":"https://pith.science/api/pith-number/6UJC5EHOIPOXRXJBOME7TMRAMS/events.json","paper":"https://pith.science/paper/6UJC5EHO"},"agent_actions":{"view_html":"https://pith.science/pith/6UJC5EHOIPOXRXJBOME7TMRAMS","download_json":"https://pith.science/pith/6UJC5EHOIPOXRXJBOME7TMRAMS.json","view_paper":"https://pith.science/paper/6UJC5EHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.02581&json=true","fetch_graph":"https://pith.science/api/pith-number/6UJC5EHOIPOXRXJBOME7TMRAMS/graph.json","fetch_events":"https://pith.science/api/pith-number/6UJC5EHOIPOXRXJBOME7TMRAMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6UJC5EHOIPOXRXJBOME7TMRAMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6UJC5EHOIPOXRXJBOME7TMRAMS/action/storage_attestation","attest_author":"https://pith.science/pith/6UJC5EHOIPOXRXJBOME7TMRAMS/action/author_attestation","sign_citation":"https://pith.science/pith/6UJC5EHOIPOXRXJBOME7TMRAMS/action/citation_signature","submit_replication":"https://pith.science/pith/6UJC5EHOIPOXRXJBOME7TMRAMS/action/replication_record"}},"created_at":"2026-05-18T00:40:36.426056+00:00","updated_at":"2026-05-18T00:40:36.426056+00:00"}