{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GSIH6BJZ4632G7SRG6ICPZMFSH","short_pith_number":"pith:GSIH6BJZ","schema_version":"1.0","canonical_sha256":"34907f0539e7b7a37e51379027e58591f0f8d9538e9e83894291da84f9057328","source":{"kind":"arxiv","id":"2411.14704","version":1},"attestation_state":"computed","paper":{"title":"Cross-Modal Pre-Aligned Method with Global and Local Information for Remote-Sensing Image and Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Andr\\'e Kaup, Gaorui Liu, Ming Zhao, Zengbao Sun","submitted_at":"2024-11-22T03:28:55Z","abstract_excerpt":"Remote sensing cross-modal text-image retrieval (RSCTIR) has gained attention for its utility in information mining. However, challenges remain in effectively integrating global and local information due to variations in remote sensing imagery and ensuring proper feature pre-alignment before modal fusion, which affects retrieval accuracy and efficiency. To address these issues, we propose CMPAGL, a cross-modal pre-aligned method leveraging global and local information. Our Gswin transformer block combines local window self-attention and global-local window cross-attention to capture multi-scal"},"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":"2411.14704","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T03:28:55Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"bc3a9f6b88bbd86d1d19f6bdbc0b6705b0038031f9d83f7f00b342d7a2ad7ed8","abstract_canon_sha256":"e80d794d37e07ea947974ff94d786d0054ff2f1cf9071bd5f8d5879b46958ff1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:55.910789Z","signature_b64":"eTyeBX74EdulpDFwRz/OcYnYGlOoLyYeKxhxOgu3ZwOvssATBq7WFefvKenTQndUwDdZiiA+VqqpzRxb8n6CBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34907f0539e7b7a37e51379027e58591f0f8d9538e9e83894291da84f9057328","last_reissued_at":"2026-07-05T09:38:55.909227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:55.909227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Modal Pre-Aligned Method with Global and Local Information for Remote-Sensing Image and Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Andr\\'e Kaup, Gaorui Liu, Ming Zhao, Zengbao Sun","submitted_at":"2024-11-22T03:28:55Z","abstract_excerpt":"Remote sensing cross-modal text-image retrieval (RSCTIR) has gained attention for its utility in information mining. However, challenges remain in effectively integrating global and local information due to variations in remote sensing imagery and ensuring proper feature pre-alignment before modal fusion, which affects retrieval accuracy and efficiency. To address these issues, we propose CMPAGL, a cross-modal pre-aligned method leveraging global and local information. Our Gswin transformer block combines local window self-attention and global-local window cross-attention to capture multi-scal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14704","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/2411.14704/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":"2411.14704","created_at":"2026-07-05T09:38:55.909336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14704v1","created_at":"2026-07-05T09:38:55.909336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14704","created_at":"2026-07-05T09:38:55.909336+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSIH6BJZ4632","created_at":"2026-07-05T09:38:55.909336+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSIH6BJZ4632G7SR","created_at":"2026-07-05T09:38:55.909336+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSIH6BJZ","created_at":"2026-07-05T09:38:55.909336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20429","citing_title":"Fast-then-Fine: A Two-Stage Framework with Multi-Granular Representation for Cross-Modal Retrieval in Remote Sensing","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GSIH6BJZ4632G7SRG6ICPZMFSH","json":"https://pith.science/pith/GSIH6BJZ4632G7SRG6ICPZMFSH.json","graph_json":"https://pith.science/api/pith-number/GSIH6BJZ4632G7SRG6ICPZMFSH/graph.json","events_json":"https://pith.science/api/pith-number/GSIH6BJZ4632G7SRG6ICPZMFSH/events.json","paper":"https://pith.science/paper/GSIH6BJZ"},"agent_actions":{"view_html":"https://pith.science/pith/GSIH6BJZ4632G7SRG6ICPZMFSH","download_json":"https://pith.science/pith/GSIH6BJZ4632G7SRG6ICPZMFSH.json","view_paper":"https://pith.science/paper/GSIH6BJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14704&json=true","fetch_graph":"https://pith.science/api/pith-number/GSIH6BJZ4632G7SRG6ICPZMFSH/graph.json","fetch_events":"https://pith.science/api/pith-number/GSIH6BJZ4632G7SRG6ICPZMFSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSIH6BJZ4632G7SRG6ICPZMFSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSIH6BJZ4632G7SRG6ICPZMFSH/action/storage_attestation","attest_author":"https://pith.science/pith/GSIH6BJZ4632G7SRG6ICPZMFSH/action/author_attestation","sign_citation":"https://pith.science/pith/GSIH6BJZ4632G7SRG6ICPZMFSH/action/citation_signature","submit_replication":"https://pith.science/pith/GSIH6BJZ4632G7SRG6ICPZMFSH/action/replication_record"}},"created_at":"2026-07-05T09:38:55.909336+00:00","updated_at":"2026-07-05T09:38:55.909336+00:00"}