{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F7QJHRY5KNY775G4JP7SSN3LQZ","short_pith_number":"pith:F7QJHRY5","schema_version":"1.0","canonical_sha256":"2fe093c71d5371fff4dc4bff29376b8672f034df677db2eb57ff9c333250aefb","source":{"kind":"arxiv","id":"2402.18233","version":2},"attestation_state":"computed","paper":{"title":"Zero-Shot Aerial Object Detection with Visual Description Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenwei Tang, Chenyu Lin, Jiancheng Lv, Tao Wang, Zhengqing Zang","submitted_at":"2024-02-28T10:58:01Z","abstract_excerpt":"Existing object detection models are mainly trained on large-scale labeled datasets. However, annotating data for novel aerial object classes is expensive since it is time-consuming and may require expert knowledge. Thus, it is desirable to study label-efficient object detection methods on aerial images. In this work, we propose a zero-shot method for aerial object detection named visual Description Regularization, or DescReg. Concretely, we identify the weak semantic-visual correlation of the aerial objects and aim to address the challenge with prior descriptions of their visual appearance. I"},"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":"2402.18233","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-28T10:58:01Z","cross_cats_sorted":[],"title_canon_sha256":"55226943b499e131009369bd7b3c77e367cd095b07b8613d5b2b306acf09b040","abstract_canon_sha256":"47b8945dd749625e4f0536ef064a2956eb9f6db270e143e8e6e7c2066435ced0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:56.715299Z","signature_b64":"6RGAmGjvMzp8kTFR7amNh0JitxcRT47/SsXyok5S1lveKrJz++b2hxYOdvmGVKWriSmuIL4Np2OMolpigsx/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fe093c71d5371fff4dc4bff29376b8672f034df677db2eb57ff9c333250aefb","last_reissued_at":"2026-07-05T07:50:56.714906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:56.714906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Aerial Object Detection with Visual Description Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenwei Tang, Chenyu Lin, Jiancheng Lv, Tao Wang, Zhengqing Zang","submitted_at":"2024-02-28T10:58:01Z","abstract_excerpt":"Existing object detection models are mainly trained on large-scale labeled datasets. However, annotating data for novel aerial object classes is expensive since it is time-consuming and may require expert knowledge. Thus, it is desirable to study label-efficient object detection methods on aerial images. In this work, we propose a zero-shot method for aerial object detection named visual Description Regularization, or DescReg. Concretely, we identify the weak semantic-visual correlation of the aerial objects and aim to address the challenge with prior descriptions of their visual appearance. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18233","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/2402.18233/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":"2402.18233","created_at":"2026-07-05T07:50:56.714979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18233v2","created_at":"2026-07-05T07:50:56.714979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18233","created_at":"2026-07-05T07:50:56.714979+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7QJHRY5KNY7","created_at":"2026-07-05T07:50:56.714979+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7QJHRY5KNY775G4","created_at":"2026-07-05T07:50:56.714979+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7QJHRY5","created_at":"2026-07-05T07:50:56.714979+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12798","citing_title":"ZoRI: Towards Discriminative Zero-Shot Remote Sensing Instance Segmentation","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F7QJHRY5KNY775G4JP7SSN3LQZ","json":"https://pith.science/pith/F7QJHRY5KNY775G4JP7SSN3LQZ.json","graph_json":"https://pith.science/api/pith-number/F7QJHRY5KNY775G4JP7SSN3LQZ/graph.json","events_json":"https://pith.science/api/pith-number/F7QJHRY5KNY775G4JP7SSN3LQZ/events.json","paper":"https://pith.science/paper/F7QJHRY5"},"agent_actions":{"view_html":"https://pith.science/pith/F7QJHRY5KNY775G4JP7SSN3LQZ","download_json":"https://pith.science/pith/F7QJHRY5KNY775G4JP7SSN3LQZ.json","view_paper":"https://pith.science/paper/F7QJHRY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18233&json=true","fetch_graph":"https://pith.science/api/pith-number/F7QJHRY5KNY775G4JP7SSN3LQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/F7QJHRY5KNY775G4JP7SSN3LQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7QJHRY5KNY775G4JP7SSN3LQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7QJHRY5KNY775G4JP7SSN3LQZ/action/storage_attestation","attest_author":"https://pith.science/pith/F7QJHRY5KNY775G4JP7SSN3LQZ/action/author_attestation","sign_citation":"https://pith.science/pith/F7QJHRY5KNY775G4JP7SSN3LQZ/action/citation_signature","submit_replication":"https://pith.science/pith/F7QJHRY5KNY775G4JP7SSN3LQZ/action/replication_record"}},"created_at":"2026-07-05T07:50:56.714979+00:00","updated_at":"2026-07-05T07:50:56.714979+00:00"}