{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:73GJVURAAJINPXYOI3OYV3PBRN","short_pith_number":"pith:73GJVURA","schema_version":"1.0","canonical_sha256":"fecc9ad2200250d7df0e46dd8aede18b551950ea410b73635eb1aebb0a55a6a3","source":{"kind":"arxiv","id":"1908.03883","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Neural Quantization for Compressed-Domain Similarity Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Artem Babenko, Stanislav Morozov","submitted_at":"2019-08-11T10:46:16Z","abstract_excerpt":"We tackle the problem of unsupervised visual descriptors compression, which is a key ingredient of large-scale image retrieval systems. While the deep learning machinery has benefited literally all computer vision pipelines, the existing state-of-the-art compression methods employ shallow architectures, and we aim to close this gap by our paper. In more detail, we introduce a DNN architecture for the unsupervised compressed-domain retrieval, based on multi-codebook quantization. The proposed architecture is designed to incorporate both fast data encoding and efficient distances computation via"},"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":"1908.03883","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-08-11T10:46:16Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"81bd805bc580c9c9ce3b34dbbefb0ddb83d82803f97e1d19d3f40fb7098c2621","abstract_canon_sha256":"2952d459ac40d5463a964cd8c7d60b283c3e25ed0efb1097af4e8283b2ce8591"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:53:19.121489Z","signature_b64":"P+tiY20ObGi+hkZtb4wsntgm81SYZWOVO0wY/586hPHwlMlUCLD/+DOyuSJiyRoTshlhzTH+ii+zGGIpRIJgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fecc9ad2200250d7df0e46dd8aede18b551950ea410b73635eb1aebb0a55a6a3","last_reissued_at":"2026-07-04T23:53:19.121125Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:53:19.121125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Neural Quantization for Compressed-Domain Similarity Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Artem Babenko, Stanislav Morozov","submitted_at":"2019-08-11T10:46:16Z","abstract_excerpt":"We tackle the problem of unsupervised visual descriptors compression, which is a key ingredient of large-scale image retrieval systems. While the deep learning machinery has benefited literally all computer vision pipelines, the existing state-of-the-art compression methods employ shallow architectures, and we aim to close this gap by our paper. In more detail, we introduce a DNN architecture for the unsupervised compressed-domain retrieval, based on multi-codebook quantization. The proposed architecture is designed to incorporate both fast data encoding and efficient distances computation via"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03883","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.03883/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1908.03883","created_at":"2026-07-04T23:53:19.121182+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.03883v1","created_at":"2026-07-04T23:53:19.121182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03883","created_at":"2026-07-04T23:53:19.121182+00:00"},{"alias_kind":"pith_short_12","alias_value":"73GJVURAAJIN","created_at":"2026-07-04T23:53:19.121182+00:00"},{"alias_kind":"pith_short_16","alias_value":"73GJVURAAJINPXYO","created_at":"2026-07-04T23:53:19.121182+00:00"},{"alias_kind":"pith_short_8","alias_value":"73GJVURA","created_at":"2026-07-04T23:53:19.121182+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/73GJVURAAJINPXYOI3OYV3PBRN","json":"https://pith.science/pith/73GJVURAAJINPXYOI3OYV3PBRN.json","graph_json":"https://pith.science/api/pith-number/73GJVURAAJINPXYOI3OYV3PBRN/graph.json","events_json":"https://pith.science/api/pith-number/73GJVURAAJINPXYOI3OYV3PBRN/events.json","paper":"https://pith.science/paper/73GJVURA"},"agent_actions":{"view_html":"https://pith.science/pith/73GJVURAAJINPXYOI3OYV3PBRN","download_json":"https://pith.science/pith/73GJVURAAJINPXYOI3OYV3PBRN.json","view_paper":"https://pith.science/paper/73GJVURA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.03883&json=true","fetch_graph":"https://pith.science/api/pith-number/73GJVURAAJINPXYOI3OYV3PBRN/graph.json","fetch_events":"https://pith.science/api/pith-number/73GJVURAAJINPXYOI3OYV3PBRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73GJVURAAJINPXYOI3OYV3PBRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73GJVURAAJINPXYOI3OYV3PBRN/action/storage_attestation","attest_author":"https://pith.science/pith/73GJVURAAJINPXYOI3OYV3PBRN/action/author_attestation","sign_citation":"https://pith.science/pith/73GJVURAAJINPXYOI3OYV3PBRN/action/citation_signature","submit_replication":"https://pith.science/pith/73GJVURAAJINPXYOI3OYV3PBRN/action/replication_record"}},"created_at":"2026-07-04T23:53:19.121182+00:00","updated_at":"2026-07-04T23:53:19.121182+00:00"}