{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:U7HMC3VGID7HJAUDXOUDYVMPNP","short_pith_number":"pith:U7HMC3VG","schema_version":"1.0","canonical_sha256":"a7cec16ea640fe748283bba83c558f6be54680ca229fd3c607e20345291d7e64","source":{"kind":"arxiv","id":"1604.01325","version":2},"attestation_state":"computed","paper":{"title":"Deep Image Retrieval: Learning global representations for image search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albert Gordo, Diane Larlus, Jerome Revaud, Jon Almazan","submitted_at":"2016-04-05T16:48:17Z","abstract_excerpt":"We propose a novel approach for instance-level image retrieval. It produces a global and compact fixed-length representation for each image by aggregating many region-wise descriptors. In contrast to previous works employing pre-trained deep networks as a black box to produce features, our method leverages a deep architecture trained for the specific task of image retrieval. Our contribution is twofold: (i) we leverage a ranking framework to learn convolution and projection weights that are used to build the region features; and (ii) we employ a region proposal network to learn which regions s"},"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":"1604.01325","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-05T16:48:17Z","cross_cats_sorted":[],"title_canon_sha256":"425b9150f80c3ecbc65f3c6e38b716224bd98c9533f4e26a23bb2f9dd75f4884","abstract_canon_sha256":"fab09658dd5df5e27ed9641128c407d2b5e284a1b5d416ca9d8799ef91be525b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:19.902714Z","signature_b64":"ZflAtNJoiTp7XPGKLqBV2jPW1k4xcTHM8pyMCi3jDNuCgzmz9eTieUBMD2CZ0oEz88Xe8n/pW79nIhryErL9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7cec16ea640fe748283bba83c558f6be54680ca229fd3c607e20345291d7e64","last_reissued_at":"2026-05-18T01:10:19.902165Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:19.902165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Image Retrieval: Learning global representations for image search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albert Gordo, Diane Larlus, Jerome Revaud, Jon Almazan","submitted_at":"2016-04-05T16:48:17Z","abstract_excerpt":"We propose a novel approach for instance-level image retrieval. It produces a global and compact fixed-length representation for each image by aggregating many region-wise descriptors. In contrast to previous works employing pre-trained deep networks as a black box to produce features, our method leverages a deep architecture trained for the specific task of image retrieval. Our contribution is twofold: (i) we leverage a ranking framework to learn convolution and projection weights that are used to build the region features; and (ii) we employ a region proposal network to learn which regions s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.01325","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":"1604.01325","created_at":"2026-05-18T01:10:19.902276+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.01325v2","created_at":"2026-05-18T01:10:19.902276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.01325","created_at":"2026-05-18T01:10:19.902276+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7HMC3VGID7H","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7HMC3VGID7HJAUD","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7HMC3VG","created_at":"2026-05-18T12:30:46.583412+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/U7HMC3VGID7HJAUDXOUDYVMPNP","json":"https://pith.science/pith/U7HMC3VGID7HJAUDXOUDYVMPNP.json","graph_json":"https://pith.science/api/pith-number/U7HMC3VGID7HJAUDXOUDYVMPNP/graph.json","events_json":"https://pith.science/api/pith-number/U7HMC3VGID7HJAUDXOUDYVMPNP/events.json","paper":"https://pith.science/paper/U7HMC3VG"},"agent_actions":{"view_html":"https://pith.science/pith/U7HMC3VGID7HJAUDXOUDYVMPNP","download_json":"https://pith.science/pith/U7HMC3VGID7HJAUDXOUDYVMPNP.json","view_paper":"https://pith.science/paper/U7HMC3VG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.01325&json=true","fetch_graph":"https://pith.science/api/pith-number/U7HMC3VGID7HJAUDXOUDYVMPNP/graph.json","fetch_events":"https://pith.science/api/pith-number/U7HMC3VGID7HJAUDXOUDYVMPNP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7HMC3VGID7HJAUDXOUDYVMPNP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7HMC3VGID7HJAUDXOUDYVMPNP/action/storage_attestation","attest_author":"https://pith.science/pith/U7HMC3VGID7HJAUDXOUDYVMPNP/action/author_attestation","sign_citation":"https://pith.science/pith/U7HMC3VGID7HJAUDXOUDYVMPNP/action/citation_signature","submit_replication":"https://pith.science/pith/U7HMC3VGID7HJAUDXOUDYVMPNP/action/replication_record"}},"created_at":"2026-05-18T01:10:19.902276+00:00","updated_at":"2026-05-18T01:10:19.902276+00:00"}