{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:27GK6HBV2GG7YDMCVAAJ6ZDP6D","short_pith_number":"pith:27GK6HBV","schema_version":"1.0","canonical_sha256":"d7ccaf1c35d18dfc0d82a8009f646ff0d44017d28ded3658c00997097f932632","source":{"kind":"arxiv","id":"2408.12246","version":3},"attestation_state":"computed","paper":{"title":"RT-OVAD: Real-Time Open-Vocabulary Aerial Object Detection via Image-Text Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunxia Zhao, Guoting Wei, Haokui Zhang, Kelu Yao, Peng Wang, Rong Xiao, Xia Yuan, Xizhe Xue, Yu Liu, Zhenhao Shang","submitted_at":"2024-08-22T09:33:25Z","abstract_excerpt":"Aerial object detection plays a crucial role in numerous applications. However, most existing methods focus on detecting predefined object categories, limiting their applicability in real-world open scenarios. In this paper, we extend aerial object detection to open scenarios through image-text collaboration and propose RT-OVAD, the first real-time open-vocabulary detector for aerial scenes. Specifically, we first introduce an image-to-text alignment loss to replace the conventional category regression loss, thereby eliminating category constraints. Next, we propose a lightweight image-text co"},"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":"2408.12246","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-22T09:33:25Z","cross_cats_sorted":[],"title_canon_sha256":"4319eea52ac2a7e21671636fc213b87b310efab62d25269cb4d8d183bce62571","abstract_canon_sha256":"dd41f8cafef0dd2d29c8a4bc660185edccc3eefc6e42278ec218feeb84e18888"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:43.101546Z","signature_b64":"z8wUHkO5ptrDSGbnhEMEu453fCUn5WLJ50fXVihmiazoA1mc9VYkoa74OFoIs0XXbE1RSue0DV7P6MNl8RHuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7ccaf1c35d18dfc0d82a8009f646ff0d44017d28ded3658c00997097f932632","last_reissued_at":"2026-07-05T11:34:43.101099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:43.101099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RT-OVAD: Real-Time Open-Vocabulary Aerial Object Detection via Image-Text Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunxia Zhao, Guoting Wei, Haokui Zhang, Kelu Yao, Peng Wang, Rong Xiao, Xia Yuan, Xizhe Xue, Yu Liu, Zhenhao Shang","submitted_at":"2024-08-22T09:33:25Z","abstract_excerpt":"Aerial object detection plays a crucial role in numerous applications. However, most existing methods focus on detecting predefined object categories, limiting their applicability in real-world open scenarios. In this paper, we extend aerial object detection to open scenarios through image-text collaboration and propose RT-OVAD, the first real-time open-vocabulary detector for aerial scenes. Specifically, we first introduce an image-to-text alignment loss to replace the conventional category regression loss, thereby eliminating category constraints. Next, we propose a lightweight image-text co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12246","kind":"arxiv","version":3},"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/2408.12246/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":"2408.12246","created_at":"2026-07-05T11:34:43.101155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12246v3","created_at":"2026-07-05T11:34:43.101155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12246","created_at":"2026-07-05T11:34:43.101155+00:00"},{"alias_kind":"pith_short_12","alias_value":"27GK6HBV2GG7","created_at":"2026-07-05T11:34:43.101155+00:00"},{"alias_kind":"pith_short_16","alias_value":"27GK6HBV2GG7YDMC","created_at":"2026-07-05T11:34:43.101155+00:00"},{"alias_kind":"pith_short_8","alias_value":"27GK6HBV","created_at":"2026-07-05T11:34:43.101155+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00338","citing_title":"DroneFINE: Domain-Aware Parameter-Efficient Fine-Tuning of Vision-Language Detectors for Drone Images","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24639","citing_title":"DisDop: Distillation with Domain Priors for Open-Vocabulary Aerial Object Detection","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/27GK6HBV2GG7YDMCVAAJ6ZDP6D","json":"https://pith.science/pith/27GK6HBV2GG7YDMCVAAJ6ZDP6D.json","graph_json":"https://pith.science/api/pith-number/27GK6HBV2GG7YDMCVAAJ6ZDP6D/graph.json","events_json":"https://pith.science/api/pith-number/27GK6HBV2GG7YDMCVAAJ6ZDP6D/events.json","paper":"https://pith.science/paper/27GK6HBV"},"agent_actions":{"view_html":"https://pith.science/pith/27GK6HBV2GG7YDMCVAAJ6ZDP6D","download_json":"https://pith.science/pith/27GK6HBV2GG7YDMCVAAJ6ZDP6D.json","view_paper":"https://pith.science/paper/27GK6HBV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12246&json=true","fetch_graph":"https://pith.science/api/pith-number/27GK6HBV2GG7YDMCVAAJ6ZDP6D/graph.json","fetch_events":"https://pith.science/api/pith-number/27GK6HBV2GG7YDMCVAAJ6ZDP6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27GK6HBV2GG7YDMCVAAJ6ZDP6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27GK6HBV2GG7YDMCVAAJ6ZDP6D/action/storage_attestation","attest_author":"https://pith.science/pith/27GK6HBV2GG7YDMCVAAJ6ZDP6D/action/author_attestation","sign_citation":"https://pith.science/pith/27GK6HBV2GG7YDMCVAAJ6ZDP6D/action/citation_signature","submit_replication":"https://pith.science/pith/27GK6HBV2GG7YDMCVAAJ6ZDP6D/action/replication_record"}},"created_at":"2026-07-05T11:34:43.101155+00:00","updated_at":"2026-07-05T11:34:43.101155+00:00"}