{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LQTTZVY56FX7BM4V2P3K6XD2PT","short_pith_number":"pith:LQTTZVY5","schema_version":"1.0","canonical_sha256":"5c273cd71df16ff0b395d3f6af5c7a7cf3b6c9a89dd20e80804289270874de55","source":{"kind":"arxiv","id":"2209.10839","version":1},"attestation_state":"computed","paper":{"title":"Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gefan Zhang, Jin Tang, Junchi Yan, Tao He, Wentao Wang, Xiaojiang Yang, Xue Yang, Yue Zhou","submitted_at":"2022-09-22T07:50:48Z","abstract_excerpt":"Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects and an additional rotation angle parameter is used for rotated objects. We argue that such a mechanism has fundamental limitations in building an effective regression loss for rotation detection, especially for high-precision detection with high IoU (e.g. 0.75). Instead, we propose to model the rotated objects as Gaussian distributions. A direct advantage is that our new regression loss regarding the distance between two Gaussians e.g. Kullback-Leibler Divergence (KLD), can well"},"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":"2209.10839","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-22T07:50:48Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c383b2ed4518686763b59d51ba9ae8b1cd3473c91208464b1cc4d571742ff28e","abstract_canon_sha256":"7cd8d7ffc9b4d2baab3a2a4ebf933739937cc847a9cdceb283ff9a8b56df140e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:07.880253Z","signature_b64":"t8kr2xxRY06R5SgrSqlcvpatX9T8OyW8hP+G6sKe1WQGOluIqrQ7Tfgmm0Nr4STy80P71CRp6APogKeKVwQNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c273cd71df16ff0b395d3f6af5c7a7cf3b6c9a89dd20e80804289270874de55","last_reissued_at":"2026-07-05T05:00:07.879917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:07.879917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gefan Zhang, Jin Tang, Junchi Yan, Tao He, Wentao Wang, Xiaojiang Yang, Xue Yang, Yue Zhou","submitted_at":"2022-09-22T07:50:48Z","abstract_excerpt":"Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects and an additional rotation angle parameter is used for rotated objects. We argue that such a mechanism has fundamental limitations in building an effective regression loss for rotation detection, especially for high-precision detection with high IoU (e.g. 0.75). Instead, we propose to model the rotated objects as Gaussian distributions. A direct advantage is that our new regression loss regarding the distance between two Gaussians e.g. Kullback-Leibler Divergence (KLD), can well"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10839","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/2209.10839/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":"2209.10839","created_at":"2026-07-05T05:00:07.879973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.10839v1","created_at":"2026-07-05T05:00:07.879973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10839","created_at":"2026-07-05T05:00:07.879973+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQTTZVY56FX7","created_at":"2026-07-05T05:00:07.879973+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQTTZVY56FX7BM4V","created_at":"2026-07-05T05:00:07.879973+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQTTZVY5","created_at":"2026-07-05T05:00:07.879973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQTTZVY56FX7BM4V2P3K6XD2PT","json":"https://pith.science/pith/LQTTZVY56FX7BM4V2P3K6XD2PT.json","graph_json":"https://pith.science/api/pith-number/LQTTZVY56FX7BM4V2P3K6XD2PT/graph.json","events_json":"https://pith.science/api/pith-number/LQTTZVY56FX7BM4V2P3K6XD2PT/events.json","paper":"https://pith.science/paper/LQTTZVY5"},"agent_actions":{"view_html":"https://pith.science/pith/LQTTZVY56FX7BM4V2P3K6XD2PT","download_json":"https://pith.science/pith/LQTTZVY56FX7BM4V2P3K6XD2PT.json","view_paper":"https://pith.science/paper/LQTTZVY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.10839&json=true","fetch_graph":"https://pith.science/api/pith-number/LQTTZVY56FX7BM4V2P3K6XD2PT/graph.json","fetch_events":"https://pith.science/api/pith-number/LQTTZVY56FX7BM4V2P3K6XD2PT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQTTZVY56FX7BM4V2P3K6XD2PT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQTTZVY56FX7BM4V2P3K6XD2PT/action/storage_attestation","attest_author":"https://pith.science/pith/LQTTZVY56FX7BM4V2P3K6XD2PT/action/author_attestation","sign_citation":"https://pith.science/pith/LQTTZVY56FX7BM4V2P3K6XD2PT/action/citation_signature","submit_replication":"https://pith.science/pith/LQTTZVY56FX7BM4V2P3K6XD2PT/action/replication_record"}},"created_at":"2026-07-05T05:00:07.879973+00:00","updated_at":"2026-07-05T05:00:07.879973+00:00"}