{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:J2D2FMCODGFGNT4DLT3JVAATIR","short_pith_number":"pith:J2D2FMCO","schema_version":"1.0","canonical_sha256":"4e87a2b04e198a66cf835cf69a80134460c7c2cd2c7f6d13de1bbc9e64b10e89","source":{"kind":"arxiv","id":"2012.15712","version":2},"attestation_state":"computed","paper":{"title":"Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Houqiang Li, Jiajun Deng, Peiwei Li, Shaoshuai Shi, Wengang Zhou, Yanyong Zhang","submitted_at":"2020-12-31T17:02:46Z","abstract_excerpt":"Recent advances on 3D object detection heavily rely on how the 3D data are represented, \\emph{i.e.}, voxel-based or point-based representation. Many existing high performance 3D detectors are point-based because this structure can better retain precise point positions. Nevertheless, point-level features lead to high computation overheads due to unordered storage. In contrast, the voxel-based structure is better suited for feature extraction but often yields lower accuracy because the input data are divided into grids. In this paper, we take a slightly different viewpoint -- we find that precis"},"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":"2012.15712","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-31T17:02:46Z","cross_cats_sorted":[],"title_canon_sha256":"944f06377e1a57db6665f497f0a0b4ca82d2de180fe33c86cea1d01db043abf3","abstract_canon_sha256":"40247a1c352e1fa7bb0cc28bc8b0a2e697766a37429a5b26450f1338d2ea6e0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:04.468797Z","signature_b64":"63KMKdqWRX1RVarvwv8SwhA7rBzQ+lQGG9Ki0jxs5MIfkkqCBoUD06F4Pls7c1zzQk03zS8Y7PWUomQU0APkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e87a2b04e198a66cf835cf69a80134460c7c2cd2c7f6d13de1bbc9e64b10e89","last_reissued_at":"2026-07-05T02:13:04.468351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:04.468351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Houqiang Li, Jiajun Deng, Peiwei Li, Shaoshuai Shi, Wengang Zhou, Yanyong Zhang","submitted_at":"2020-12-31T17:02:46Z","abstract_excerpt":"Recent advances on 3D object detection heavily rely on how the 3D data are represented, \\emph{i.e.}, voxel-based or point-based representation. Many existing high performance 3D detectors are point-based because this structure can better retain precise point positions. Nevertheless, point-level features lead to high computation overheads due to unordered storage. In contrast, the voxel-based structure is better suited for feature extraction but often yields lower accuracy because the input data are divided into grids. In this paper, we take a slightly different viewpoint -- we find that precis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15712","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/2012.15712/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":"2012.15712","created_at":"2026-07-05T02:13:04.468417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.15712v2","created_at":"2026-07-05T02:13:04.468417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15712","created_at":"2026-07-05T02:13:04.468417+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2D2FMCODGFG","created_at":"2026-07-05T02:13:04.468417+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2D2FMCODGFGNT4D","created_at":"2026-07-05T02:13:04.468417+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2D2FMCO","created_at":"2026-07-05T02:13:04.468417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04123","citing_title":"Towards Accurate and Efficient 3D Object Detection for Autonomous Driving: A Mixture of Experts Computing System on Edge","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J2D2FMCODGFGNT4DLT3JVAATIR","json":"https://pith.science/pith/J2D2FMCODGFGNT4DLT3JVAATIR.json","graph_json":"https://pith.science/api/pith-number/J2D2FMCODGFGNT4DLT3JVAATIR/graph.json","events_json":"https://pith.science/api/pith-number/J2D2FMCODGFGNT4DLT3JVAATIR/events.json","paper":"https://pith.science/paper/J2D2FMCO"},"agent_actions":{"view_html":"https://pith.science/pith/J2D2FMCODGFGNT4DLT3JVAATIR","download_json":"https://pith.science/pith/J2D2FMCODGFGNT4DLT3JVAATIR.json","view_paper":"https://pith.science/paper/J2D2FMCO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.15712&json=true","fetch_graph":"https://pith.science/api/pith-number/J2D2FMCODGFGNT4DLT3JVAATIR/graph.json","fetch_events":"https://pith.science/api/pith-number/J2D2FMCODGFGNT4DLT3JVAATIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2D2FMCODGFGNT4DLT3JVAATIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2D2FMCODGFGNT4DLT3JVAATIR/action/storage_attestation","attest_author":"https://pith.science/pith/J2D2FMCODGFGNT4DLT3JVAATIR/action/author_attestation","sign_citation":"https://pith.science/pith/J2D2FMCODGFGNT4DLT3JVAATIR/action/citation_signature","submit_replication":"https://pith.science/pith/J2D2FMCODGFGNT4DLT3JVAATIR/action/replication_record"}},"created_at":"2026-07-05T02:13:04.468417+00:00","updated_at":"2026-07-05T02:13:04.468417+00:00"}