{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:2F6ONA2FPVVOGAQDR63B3E67KJ","short_pith_number":"pith:2F6ONA2F","schema_version":"1.0","canonical_sha256":"d17ce683457d6ae302038fb61d93df5250f30cbfa7aa0a40dc7100f7e91a34bd","source":{"kind":"arxiv","id":"1501.04711","version":1},"attestation_state":"computed","paper":{"title":"DeepHash: Getting Regularization, Depth and Fine-Tuning Right","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Antoine Veillard, Hanlin Goh, Jie Lin, Olivier Morere, Vijay Chandrasekhar","submitted_at":"2015-01-20T04:36:12Z","abstract_excerpt":"This work focuses on representing very high-dimensional global image descriptors using very compact 64-1024 bit binary hashes for instance retrieval. We propose DeepHash: a hashing scheme based on deep networks. Key to making DeepHash work at extremely low bitrates are three important considerations -- regularization, depth and fine-tuning -- each requiring solutions specific to the hashing problem. In-depth evaluation shows that our scheme consistently outperforms state-of-the-art methods across all data sets for both Fisher Vectors and Deep Convolutional Neural Network features, by up to 20 "},"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":"1501.04711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-01-20T04:36:12Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"d67097369b0c367201a74eebaa3df4d7dd586713d963c4ca11d4a9cababb9811","abstract_canon_sha256":"717e60b81b49fb2d8dcdebb99c1afecd8d4a8c9e7a1ba08f176b23028ce14420"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:47.109921Z","signature_b64":"uD9/RZOiqdmpHXE2/G8sn6AL4uO8thEFJMupS8Ycwb2RJ/6oSw6oUxUOVIAaho5oMFaNiyoOPajdwB9acy+BCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d17ce683457d6ae302038fb61d93df5250f30cbfa7aa0a40dc7100f7e91a34bd","last_reissued_at":"2026-05-18T01:20:47.109430Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:47.109430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepHash: Getting Regularization, Depth and Fine-Tuning Right","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Antoine Veillard, Hanlin Goh, Jie Lin, Olivier Morere, Vijay Chandrasekhar","submitted_at":"2015-01-20T04:36:12Z","abstract_excerpt":"This work focuses on representing very high-dimensional global image descriptors using very compact 64-1024 bit binary hashes for instance retrieval. We propose DeepHash: a hashing scheme based on deep networks. Key to making DeepHash work at extremely low bitrates are three important considerations -- regularization, depth and fine-tuning -- each requiring solutions specific to the hashing problem. In-depth evaluation shows that our scheme consistently outperforms state-of-the-art methods across all data sets for both Fisher Vectors and Deep Convolutional Neural Network features, by up to 20 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.04711","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":"1501.04711","created_at":"2026-05-18T01:20:47.109535+00:00"},{"alias_kind":"arxiv_version","alias_value":"1501.04711v1","created_at":"2026-05-18T01:20:47.109535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.04711","created_at":"2026-05-18T01:20:47.109535+00:00"},{"alias_kind":"pith_short_12","alias_value":"2F6ONA2FPVVO","created_at":"2026-05-18T12:28:59.999130+00:00"},{"alias_kind":"pith_short_16","alias_value":"2F6ONA2FPVVOGAQD","created_at":"2026-05-18T12:28:59.999130+00:00"},{"alias_kind":"pith_short_8","alias_value":"2F6ONA2F","created_at":"2026-05-18T12:28:59.999130+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/2F6ONA2FPVVOGAQDR63B3E67KJ","json":"https://pith.science/pith/2F6ONA2FPVVOGAQDR63B3E67KJ.json","graph_json":"https://pith.science/api/pith-number/2F6ONA2FPVVOGAQDR63B3E67KJ/graph.json","events_json":"https://pith.science/api/pith-number/2F6ONA2FPVVOGAQDR63B3E67KJ/events.json","paper":"https://pith.science/paper/2F6ONA2F"},"agent_actions":{"view_html":"https://pith.science/pith/2F6ONA2FPVVOGAQDR63B3E67KJ","download_json":"https://pith.science/pith/2F6ONA2FPVVOGAQDR63B3E67KJ.json","view_paper":"https://pith.science/paper/2F6ONA2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1501.04711&json=true","fetch_graph":"https://pith.science/api/pith-number/2F6ONA2FPVVOGAQDR63B3E67KJ/graph.json","fetch_events":"https://pith.science/api/pith-number/2F6ONA2FPVVOGAQDR63B3E67KJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2F6ONA2FPVVOGAQDR63B3E67KJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2F6ONA2FPVVOGAQDR63B3E67KJ/action/storage_attestation","attest_author":"https://pith.science/pith/2F6ONA2FPVVOGAQDR63B3E67KJ/action/author_attestation","sign_citation":"https://pith.science/pith/2F6ONA2FPVVOGAQDR63B3E67KJ/action/citation_signature","submit_replication":"https://pith.science/pith/2F6ONA2FPVVOGAQDR63B3E67KJ/action/replication_record"}},"created_at":"2026-05-18T01:20:47.109535+00:00","updated_at":"2026-05-18T01:20:47.109535+00:00"}