{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4TZWPISJ7IVEFIKJZJGZJV7K3T","short_pith_number":"pith:4TZWPISJ","schema_version":"1.0","canonical_sha256":"e4f367a249fa2a42a149ca4d94d7eadcf33a70793674fc2a0f93382a1dd809d3","source":{"kind":"arxiv","id":"1906.04087","version":2},"attestation_state":"computed","paper":{"title":"Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kohei Ozaki, Shuhei Yokoo","submitted_at":"2019-06-10T16:00:06Z","abstract_excerpt":"The Google-Landmarks-v2 dataset is the biggest worldwide landmarks dataset characterized by a large magnitude of noisiness and diversity. We present a novel landmark retrieval/recognition system, robust to a noisy and diverse dataset, by our team, smlyaka. Our approach is based on deep convolutional neural networks with metric learning, trained by cosine-softmax based losses. Deep metric learning methods are usually sensitive to noise, and it could hinder to learn a reliable metric. To address this issue, we develop an automated data cleaning system. Besides, we devise a discriminative re-rank"},"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":"1906.04087","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-10T16:00:06Z","cross_cats_sorted":[],"title_canon_sha256":"9f278032920dd31509be6613b1bfdd597fbd243c3536a140d17826367091e27f","abstract_canon_sha256":"986b048a03660e2e042a6dc6eecd454e35e4ef5a603126532c21b5c6faeb612c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:42.059114Z","signature_b64":"UhBVbbzQQ+faxciM0w7mHvPe7RYRSR9mcczr+3a471SocCmbrMx3Z1c485nbSKVc300sSBIJHMFN8bxE5pQUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4f367a249fa2a42a149ca4d94d7eadcf33a70793674fc2a0f93382a1dd809d3","last_reissued_at":"2026-05-17T23:43:42.058542Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:42.058542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kohei Ozaki, Shuhei Yokoo","submitted_at":"2019-06-10T16:00:06Z","abstract_excerpt":"The Google-Landmarks-v2 dataset is the biggest worldwide landmarks dataset characterized by a large magnitude of noisiness and diversity. We present a novel landmark retrieval/recognition system, robust to a noisy and diverse dataset, by our team, smlyaka. Our approach is based on deep convolutional neural networks with metric learning, trained by cosine-softmax based losses. Deep metric learning methods are usually sensitive to noise, and it could hinder to learn a reliable metric. To address this issue, we develop an automated data cleaning system. Besides, we devise a discriminative re-rank"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04087","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":"1906.04087","created_at":"2026-05-17T23:43:42.058633+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.04087v2","created_at":"2026-05-17T23:43:42.058633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04087","created_at":"2026-05-17T23:43:42.058633+00:00"},{"alias_kind":"pith_short_12","alias_value":"4TZWPISJ7IVE","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"4TZWPISJ7IVEFIKJ","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"4TZWPISJ","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11063","citing_title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4TZWPISJ7IVEFIKJZJGZJV7K3T","json":"https://pith.science/pith/4TZWPISJ7IVEFIKJZJGZJV7K3T.json","graph_json":"https://pith.science/api/pith-number/4TZWPISJ7IVEFIKJZJGZJV7K3T/graph.json","events_json":"https://pith.science/api/pith-number/4TZWPISJ7IVEFIKJZJGZJV7K3T/events.json","paper":"https://pith.science/paper/4TZWPISJ"},"agent_actions":{"view_html":"https://pith.science/pith/4TZWPISJ7IVEFIKJZJGZJV7K3T","download_json":"https://pith.science/pith/4TZWPISJ7IVEFIKJZJGZJV7K3T.json","view_paper":"https://pith.science/paper/4TZWPISJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.04087&json=true","fetch_graph":"https://pith.science/api/pith-number/4TZWPISJ7IVEFIKJZJGZJV7K3T/graph.json","fetch_events":"https://pith.science/api/pith-number/4TZWPISJ7IVEFIKJZJGZJV7K3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4TZWPISJ7IVEFIKJZJGZJV7K3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4TZWPISJ7IVEFIKJZJGZJV7K3T/action/storage_attestation","attest_author":"https://pith.science/pith/4TZWPISJ7IVEFIKJZJGZJV7K3T/action/author_attestation","sign_citation":"https://pith.science/pith/4TZWPISJ7IVEFIKJZJGZJV7K3T/action/citation_signature","submit_replication":"https://pith.science/pith/4TZWPISJ7IVEFIKJZJGZJV7K3T/action/replication_record"}},"created_at":"2026-05-17T23:43:42.058633+00:00","updated_at":"2026-05-17T23:43:42.058633+00:00"}