{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AMNQETO5C5EXILMLATFZBOGBTE","short_pith_number":"pith:AMNQETO5","schema_version":"1.0","canonical_sha256":"031b024ddd1749742d8b04cb90b8c199214a28d8eb746820b5b75508bedc32e6","source":{"kind":"arxiv","id":"1911.08877","version":1},"attestation_state":"computed","paper":{"title":"Improving Semantic Segmentation of Aerial Images Using Patch-based Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Tang, Lei Ding, Lorenzo Bruzzone","submitted_at":"2019-11-20T13:12:04Z","abstract_excerpt":"The trade-off between feature representation power and spatial localization accuracy is crucial for the dense classification/semantic segmentation of aerial images. High-level features extracted from the late layers of a neural network are rich in semantic information, yet have blurred spatial details; low-level features extracted from the early layers of a network contain more pixel-level information, but are isolated and noisy. It is therefore difficult to bridge the gap between high and low-level features due to their difference in terms of physical information content and spatial distribut"},"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":"1911.08877","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-20T13:12:04Z","cross_cats_sorted":[],"title_canon_sha256":"9d8d96f088e308943aeb20106b437c0c94bd0f841a5a8e50d23cfe8b53647f1a","abstract_canon_sha256":"ca79ae94fcdf7da8aa6ec8ddfcf8870890a1861a5d833fcf16c172051460e641"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:56.251340Z","signature_b64":"YI0KuhcgHkm/gBMMrg/rKVEhYBzFoyLOUvplMx/fDzJrzKjXd9g6D5blLxQtsXI1X2QS7ODYmXtRPjyQqbUfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"031b024ddd1749742d8b04cb90b8c199214a28d8eb746820b5b75508bedc32e6","last_reissued_at":"2026-07-05T02:52:56.250913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:56.250913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Semantic Segmentation of Aerial Images Using Patch-based Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Tang, Lei Ding, Lorenzo Bruzzone","submitted_at":"2019-11-20T13:12:04Z","abstract_excerpt":"The trade-off between feature representation power and spatial localization accuracy is crucial for the dense classification/semantic segmentation of aerial images. High-level features extracted from the late layers of a neural network are rich in semantic information, yet have blurred spatial details; low-level features extracted from the early layers of a network contain more pixel-level information, but are isolated and noisy. It is therefore difficult to bridge the gap between high and low-level features due to their difference in terms of physical information content and spatial distribut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.08877","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/1911.08877/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":"1911.08877","created_at":"2026-07-05T02:52:56.250969+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.08877v1","created_at":"2026-07-05T02:52:56.250969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.08877","created_at":"2026-07-05T02:52:56.250969+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMNQETO5C5EX","created_at":"2026-07-05T02:52:56.250969+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMNQETO5C5EXILML","created_at":"2026-07-05T02:52:56.250969+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMNQETO5","created_at":"2026-07-05T02:52:56.250969+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25300","citing_title":"DenseScout: Algorithm-System Co-design for Budgeted Tiny Object Selection on Edge Platforms","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AMNQETO5C5EXILMLATFZBOGBTE","json":"https://pith.science/pith/AMNQETO5C5EXILMLATFZBOGBTE.json","graph_json":"https://pith.science/api/pith-number/AMNQETO5C5EXILMLATFZBOGBTE/graph.json","events_json":"https://pith.science/api/pith-number/AMNQETO5C5EXILMLATFZBOGBTE/events.json","paper":"https://pith.science/paper/AMNQETO5"},"agent_actions":{"view_html":"https://pith.science/pith/AMNQETO5C5EXILMLATFZBOGBTE","download_json":"https://pith.science/pith/AMNQETO5C5EXILMLATFZBOGBTE.json","view_paper":"https://pith.science/paper/AMNQETO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.08877&json=true","fetch_graph":"https://pith.science/api/pith-number/AMNQETO5C5EXILMLATFZBOGBTE/graph.json","fetch_events":"https://pith.science/api/pith-number/AMNQETO5C5EXILMLATFZBOGBTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMNQETO5C5EXILMLATFZBOGBTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMNQETO5C5EXILMLATFZBOGBTE/action/storage_attestation","attest_author":"https://pith.science/pith/AMNQETO5C5EXILMLATFZBOGBTE/action/author_attestation","sign_citation":"https://pith.science/pith/AMNQETO5C5EXILMLATFZBOGBTE/action/citation_signature","submit_replication":"https://pith.science/pith/AMNQETO5C5EXILMLATFZBOGBTE/action/replication_record"}},"created_at":"2026-07-05T02:52:56.250969+00:00","updated_at":"2026-07-05T02:52:56.250969+00:00"}