{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WMZXVJDNMW4AMXIGPXE3LOXL4P","short_pith_number":"pith:WMZXVJDN","schema_version":"1.0","canonical_sha256":"b3337aa46d65b8065d067dc9b5baebe3fa0ac20b45df395d629ed922d06d03e0","source":{"kind":"arxiv","id":"2006.03926","version":2},"attestation_state":"computed","paper":{"title":"Self-supervising Fine-grained Region Similarities for Large-scale Image Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhu, Haibo Wang, Hongsheng Li, Rui Zhao, Yixiao Ge","submitted_at":"2020-06-06T17:31:52Z","abstract_excerpt":"The task of large-scale retrieval-based image localization is to estimate the geographical location of a query image by recognizing its nearest reference images from a city-scale dataset. However, the general public benchmarks only provide noisy GPS labels associated with the training images, which act as weak supervisions for learning image-to-image similarities. Such label noise prevents deep neural networks from learning discriminative features for accurate localization. To tackle this challenge, we propose to self-supervise image-to-region similarities in order to fully explore the potenti"},"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":"2006.03926","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-06T17:31:52Z","cross_cats_sorted":[],"title_canon_sha256":"7132da2f624b5624de7ab7fc9a10fc21451b39eb6bdf885648ad9408ea39ad0e","abstract_canon_sha256":"56262d84a8b351cf553022d7572aa29d1d0222409fdf46e099c6a3d8c5fb4db2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:28.053336Z","signature_b64":"TNb4eQcJe5HlleIlKvA6Wg2dAsLLgSV3xOmBez8q1UhVFOuZlVSVe16QGFd6Anad3eJvCvbN+CCpN3ha9m6TAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3337aa46d65b8065d067dc9b5baebe3fa0ac20b45df395d629ed922d06d03e0","last_reissued_at":"2026-07-05T01:17:28.052972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:28.052972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervising Fine-grained Region Similarities for Large-scale Image Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhu, Haibo Wang, Hongsheng Li, Rui Zhao, Yixiao Ge","submitted_at":"2020-06-06T17:31:52Z","abstract_excerpt":"The task of large-scale retrieval-based image localization is to estimate the geographical location of a query image by recognizing its nearest reference images from a city-scale dataset. However, the general public benchmarks only provide noisy GPS labels associated with the training images, which act as weak supervisions for learning image-to-image similarities. Such label noise prevents deep neural networks from learning discriminative features for accurate localization. To tackle this challenge, we propose to self-supervise image-to-region similarities in order to fully explore the potenti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.03926","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.03926/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":"2006.03926","created_at":"2026-07-05T01:17:28.053024+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.03926v2","created_at":"2026-07-05T01:17:28.053024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.03926","created_at":"2026-07-05T01:17:28.053024+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMZXVJDNMW4A","created_at":"2026-07-05T01:17:28.053024+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMZXVJDNMW4AMXIG","created_at":"2026-07-05T01:17:28.053024+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMZXVJDN","created_at":"2026-07-05T01:17:28.053024+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/WMZXVJDNMW4AMXIGPXE3LOXL4P","json":"https://pith.science/pith/WMZXVJDNMW4AMXIGPXE3LOXL4P.json","graph_json":"https://pith.science/api/pith-number/WMZXVJDNMW4AMXIGPXE3LOXL4P/graph.json","events_json":"https://pith.science/api/pith-number/WMZXVJDNMW4AMXIGPXE3LOXL4P/events.json","paper":"https://pith.science/paper/WMZXVJDN"},"agent_actions":{"view_html":"https://pith.science/pith/WMZXVJDNMW4AMXIGPXE3LOXL4P","download_json":"https://pith.science/pith/WMZXVJDNMW4AMXIGPXE3LOXL4P.json","view_paper":"https://pith.science/paper/WMZXVJDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.03926&json=true","fetch_graph":"https://pith.science/api/pith-number/WMZXVJDNMW4AMXIGPXE3LOXL4P/graph.json","fetch_events":"https://pith.science/api/pith-number/WMZXVJDNMW4AMXIGPXE3LOXL4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMZXVJDNMW4AMXIGPXE3LOXL4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMZXVJDNMW4AMXIGPXE3LOXL4P/action/storage_attestation","attest_author":"https://pith.science/pith/WMZXVJDNMW4AMXIGPXE3LOXL4P/action/author_attestation","sign_citation":"https://pith.science/pith/WMZXVJDNMW4AMXIGPXE3LOXL4P/action/citation_signature","submit_replication":"https://pith.science/pith/WMZXVJDNMW4AMXIGPXE3LOXL4P/action/replication_record"}},"created_at":"2026-07-05T01:17:28.053024+00:00","updated_at":"2026-07-05T01:17:28.053024+00:00"}