{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OLFAHVKSFJLWPK2QWTBE4CQ5GG","short_pith_number":"pith:OLFAHVKS","schema_version":"1.0","canonical_sha256":"72ca03d5522a5767ab50b4c24e0a1d319e23218b7cacc4c4884feac19f542f38","source":{"kind":"arxiv","id":"2211.12501","version":3},"attestation_state":"computed","paper":{"title":"AeDet: Azimuth-invariant Multi-view 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjian Feng, Lin Ma, Xiangxiang Chu, Yujie Zhong, Zequn Jie","submitted_at":"2022-11-22T18:59:52Z","abstract_excerpt":"Recent LSS-based multi-view 3D object detection has made tremendous progress, by processing the features in Brid-Eye-View (BEV) via the convolutional detector. However, the typical convolution ignores the radial symmetry of the BEV features and increases the difficulty of the detector optimization. To preserve the inherent property of the BEV features and ease the optimization, we propose an azimuth-equivariant convolution (AeConv) and an azimuth-equivariant anchor. The sampling grid of AeConv is always in the radial direction, thus it can learn azimuth-invariant BEV features. The proposed anc"},"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":"2211.12501","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T18:59:52Z","cross_cats_sorted":[],"title_canon_sha256":"804386eb1667b9650f92d4d1da062aba4e87bce1eed0f25df898e4ee844e8386","abstract_canon_sha256":"cb7582d408f1d01ca7188e2c6f3bc29cc1b6dbb0809797f61dd52d15f46ddc62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:34.464220Z","signature_b64":"AVbNT1STVP4JQBdYNNmc+c/JnHig7NwmfBPJQfc7/nH8y+UG42BQGJVdc1XbhGUmP+xeURwX24qJZJNv6TpsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72ca03d5522a5767ab50b4c24e0a1d319e23218b7cacc4c4884feac19f542f38","last_reissued_at":"2026-07-05T05:57:34.463798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:34.463798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AeDet: Azimuth-invariant Multi-view 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjian Feng, Lin Ma, Xiangxiang Chu, Yujie Zhong, Zequn Jie","submitted_at":"2022-11-22T18:59:52Z","abstract_excerpt":"Recent LSS-based multi-view 3D object detection has made tremendous progress, by processing the features in Brid-Eye-View (BEV) via the convolutional detector. However, the typical convolution ignores the radial symmetry of the BEV features and increases the difficulty of the detector optimization. To preserve the inherent property of the BEV features and ease the optimization, we propose an azimuth-equivariant convolution (AeConv) and an azimuth-equivariant anchor. The sampling grid of AeConv is always in the radial direction, thus it can learn azimuth-invariant BEV features. The proposed anc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12501","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/2211.12501/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":"2211.12501","created_at":"2026-07-05T05:57:34.463855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12501v3","created_at":"2026-07-05T05:57:34.463855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12501","created_at":"2026-07-05T05:57:34.463855+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLFAHVKSFJLW","created_at":"2026-07-05T05:57:34.463855+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLFAHVKSFJLWPK2Q","created_at":"2026-07-05T05:57:34.463855+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLFAHVKS","created_at":"2026-07-05T05:57:34.463855+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19593","citing_title":"Generalizing Monocular 3D Object Detection","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OLFAHVKSFJLWPK2QWTBE4CQ5GG","json":"https://pith.science/pith/OLFAHVKSFJLWPK2QWTBE4CQ5GG.json","graph_json":"https://pith.science/api/pith-number/OLFAHVKSFJLWPK2QWTBE4CQ5GG/graph.json","events_json":"https://pith.science/api/pith-number/OLFAHVKSFJLWPK2QWTBE4CQ5GG/events.json","paper":"https://pith.science/paper/OLFAHVKS"},"agent_actions":{"view_html":"https://pith.science/pith/OLFAHVKSFJLWPK2QWTBE4CQ5GG","download_json":"https://pith.science/pith/OLFAHVKSFJLWPK2QWTBE4CQ5GG.json","view_paper":"https://pith.science/paper/OLFAHVKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12501&json=true","fetch_graph":"https://pith.science/api/pith-number/OLFAHVKSFJLWPK2QWTBE4CQ5GG/graph.json","fetch_events":"https://pith.science/api/pith-number/OLFAHVKSFJLWPK2QWTBE4CQ5GG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLFAHVKSFJLWPK2QWTBE4CQ5GG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLFAHVKSFJLWPK2QWTBE4CQ5GG/action/storage_attestation","attest_author":"https://pith.science/pith/OLFAHVKSFJLWPK2QWTBE4CQ5GG/action/author_attestation","sign_citation":"https://pith.science/pith/OLFAHVKSFJLWPK2QWTBE4CQ5GG/action/citation_signature","submit_replication":"https://pith.science/pith/OLFAHVKSFJLWPK2QWTBE4CQ5GG/action/replication_record"}},"created_at":"2026-07-05T05:57:34.463855+00:00","updated_at":"2026-07-05T05:57:34.463855+00:00"}