{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q46B7UP62GDVC2W5TT3ZLDAFE6","short_pith_number":"pith:Q46B7UP6","schema_version":"1.0","canonical_sha256":"873c1fd1fed187516add9cf7958c0527b8adeec6ce270bf75513966ebaf6c4ce","source":{"kind":"arxiv","id":"2412.17007","version":2},"attestation_state":"computed","paper":{"title":"Where am I? Cross-View Geo-localization with Natural Language Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Conghui He, Dairong Chen, Honglin Lin, Junyan Ye, Leyan Ou, Qi Zhu, Weijia Li, Zihao Wang","submitted_at":"2024-12-22T13:13:10Z","abstract_excerpt":"Cross-view geo-localization identifies the locations of street-view images by matching them with geo-tagged satellite images or OSM. However, most existing studies focus on image-to-image retrieval, with fewer addressing text-guided retrieval, a task vital for applications like pedestrian navigation and emergency response. In this work, we introduce a novel task for cross-view geo-localization with natural language descriptions, which aims to retrieve corresponding satellite images or OSM database based on scene text descriptions. To support this task, we construct the CVG-Text dataset by coll"},"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":"2412.17007","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-22T13:13:10Z","cross_cats_sorted":[],"title_canon_sha256":"949249ddeded03b4d030e54b284ad89ff35f5311b639b3b4f29cd6cc3736ddca","abstract_canon_sha256":"5784d54fbc1d030041a80bb5bb4ac3112cd13a14d76dd549120bdcbd2d85ce5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:14.456085Z","signature_b64":"QAlRTeA++XsWKy6HmCiYLIMSS5fbdGEoX6bsojbuXW02fJNb5uKl4eZTd3korLNdUPn6v50YQlSa8yvj13kUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"873c1fd1fed187516add9cf7958c0527b8adeec6ce270bf75513966ebaf6c4ce","last_reissued_at":"2026-07-05T10:42:14.455609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:14.455609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Where am I? Cross-View Geo-localization with Natural Language Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Conghui He, Dairong Chen, Honglin Lin, Junyan Ye, Leyan Ou, Qi Zhu, Weijia Li, Zihao Wang","submitted_at":"2024-12-22T13:13:10Z","abstract_excerpt":"Cross-view geo-localization identifies the locations of street-view images by matching them with geo-tagged satellite images or OSM. However, most existing studies focus on image-to-image retrieval, with fewer addressing text-guided retrieval, a task vital for applications like pedestrian navigation and emergency response. In this work, we introduce a novel task for cross-view geo-localization with natural language descriptions, which aims to retrieve corresponding satellite images or OSM database based on scene text descriptions. To support this task, we construct the CVG-Text dataset by coll"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17007","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/2412.17007/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":"2412.17007","created_at":"2026-07-05T10:42:14.455668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17007v2","created_at":"2026-07-05T10:42:14.455668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17007","created_at":"2026-07-05T10:42:14.455668+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q46B7UP62GDV","created_at":"2026-07-05T10:42:14.455668+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q46B7UP62GDVC2W5","created_at":"2026-07-05T10:42:14.455668+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q46B7UP6","created_at":"2026-07-05T10:42:14.455668+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.02697","citing_title":"GeoBridge: A Semantic-Anchored Multi-View Foundation Model Bridging Images and Text for Geo-Localization","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q46B7UP62GDVC2W5TT3ZLDAFE6","json":"https://pith.science/pith/Q46B7UP62GDVC2W5TT3ZLDAFE6.json","graph_json":"https://pith.science/api/pith-number/Q46B7UP62GDVC2W5TT3ZLDAFE6/graph.json","events_json":"https://pith.science/api/pith-number/Q46B7UP62GDVC2W5TT3ZLDAFE6/events.json","paper":"https://pith.science/paper/Q46B7UP6"},"agent_actions":{"view_html":"https://pith.science/pith/Q46B7UP62GDVC2W5TT3ZLDAFE6","download_json":"https://pith.science/pith/Q46B7UP62GDVC2W5TT3ZLDAFE6.json","view_paper":"https://pith.science/paper/Q46B7UP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17007&json=true","fetch_graph":"https://pith.science/api/pith-number/Q46B7UP62GDVC2W5TT3ZLDAFE6/graph.json","fetch_events":"https://pith.science/api/pith-number/Q46B7UP62GDVC2W5TT3ZLDAFE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q46B7UP62GDVC2W5TT3ZLDAFE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q46B7UP62GDVC2W5TT3ZLDAFE6/action/storage_attestation","attest_author":"https://pith.science/pith/Q46B7UP62GDVC2W5TT3ZLDAFE6/action/author_attestation","sign_citation":"https://pith.science/pith/Q46B7UP62GDVC2W5TT3ZLDAFE6/action/citation_signature","submit_replication":"https://pith.science/pith/Q46B7UP62GDVC2W5TT3ZLDAFE6/action/replication_record"}},"created_at":"2026-07-05T10:42:14.455668+00:00","updated_at":"2026-07-05T10:42:14.455668+00:00"}