{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:N2DLEXEVJ4SK2IO7CVRG45XWFS","short_pith_number":"pith:N2DLEXEV","schema_version":"1.0","canonical_sha256":"6e86b25c954f24ad21df15626e76f62c8a63dfebc864b02c27b6d2d2c9aaf8d6","source":{"kind":"arxiv","id":"1511.05879","version":2},"attestation_state":"computed","paper":{"title":"Particular object retrieval with integral max-pooling of CNN activations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Giorgos Tolias, Herv\\'e J\\'egou, Ronan Sicre","submitted_at":"2015-11-18T17:02:59Z","abstract_excerpt":"Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations. Yet such models are not compatible with geometry-aware re-ranking methods and still outperformed, on some particular object retrieval benchmarks, by traditional image search systems relying on precise descriptor matching, geometric re-ranking, or query expansion. This work revisits both retrieval stages, namely initial search and re-ranking, by employing the same primitive information deriv"},"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":"1511.05879","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-18T17:02:59Z","cross_cats_sorted":[],"title_canon_sha256":"a63f84434b0a2e2d281322cc509f6673851ddbf81e0fda6480822f1cd9bf6094","abstract_canon_sha256":"126e12827a5807201cdda6d8137c157e736bd4e8a4f6c72602ab9d68e27a8332"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:03.344055Z","signature_b64":"7DH7uh/ebBV0393FmK7/HRK5yTLlHjRtoxFZE4jbf48mFQqqiDCIiFUqNsX/0kWXOE8FviDbKaH8Nxel9Ma9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e86b25c954f24ad21df15626e76f62c8a63dfebc864b02c27b6d2d2c9aaf8d6","last_reissued_at":"2026-05-18T01:20:03.343467Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:03.343467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Particular object retrieval with integral max-pooling of CNN activations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Giorgos Tolias, Herv\\'e J\\'egou, Ronan Sicre","submitted_at":"2015-11-18T17:02:59Z","abstract_excerpt":"Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations. Yet such models are not compatible with geometry-aware re-ranking methods and still outperformed, on some particular object retrieval benchmarks, by traditional image search systems relying on precise descriptor matching, geometric re-ranking, or query expansion. This work revisits both retrieval stages, namely initial search and re-ranking, by employing the same primitive information deriv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05879","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":"1511.05879","created_at":"2026-05-18T01:20:03.343554+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.05879v2","created_at":"2026-05-18T01:20:03.343554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05879","created_at":"2026-05-18T01:20:03.343554+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2DLEXEVJ4SK","created_at":"2026-05-18T12:29:32.376354+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2DLEXEVJ4SK2IO7","created_at":"2026-05-18T12:29:32.376354+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2DLEXEV","created_at":"2026-05-18T12:29:32.376354+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.11419","citing_title":"Automatic Coverage Selection for Surface-Based Visual Localization","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2104.14294","citing_title":"Emerging Properties in Self-Supervised Vision Transformers","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14037","citing_title":"Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2604.00809","citing_title":"Revisiting Human-in-the-Loop Object Retrieval with Pre-Trained Vision Transformers","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2DLEXEVJ4SK2IO7CVRG45XWFS","json":"https://pith.science/pith/N2DLEXEVJ4SK2IO7CVRG45XWFS.json","graph_json":"https://pith.science/api/pith-number/N2DLEXEVJ4SK2IO7CVRG45XWFS/graph.json","events_json":"https://pith.science/api/pith-number/N2DLEXEVJ4SK2IO7CVRG45XWFS/events.json","paper":"https://pith.science/paper/N2DLEXEV"},"agent_actions":{"view_html":"https://pith.science/pith/N2DLEXEVJ4SK2IO7CVRG45XWFS","download_json":"https://pith.science/pith/N2DLEXEVJ4SK2IO7CVRG45XWFS.json","view_paper":"https://pith.science/paper/N2DLEXEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.05879&json=true","fetch_graph":"https://pith.science/api/pith-number/N2DLEXEVJ4SK2IO7CVRG45XWFS/graph.json","fetch_events":"https://pith.science/api/pith-number/N2DLEXEVJ4SK2IO7CVRG45XWFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2DLEXEVJ4SK2IO7CVRG45XWFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2DLEXEVJ4SK2IO7CVRG45XWFS/action/storage_attestation","attest_author":"https://pith.science/pith/N2DLEXEVJ4SK2IO7CVRG45XWFS/action/author_attestation","sign_citation":"https://pith.science/pith/N2DLEXEVJ4SK2IO7CVRG45XWFS/action/citation_signature","submit_replication":"https://pith.science/pith/N2DLEXEVJ4SK2IO7CVRG45XWFS/action/replication_record"}},"created_at":"2026-05-18T01:20:03.343554+00:00","updated_at":"2026-05-18T01:20:03.343554+00:00"}