{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DEQLVIXKTWAY2642JRE54NERMX","short_pith_number":"pith:DEQLVIXK","schema_version":"1.0","canonical_sha256":"1920baa2ea9d818d7b9a4c49de349165eaf1700a93b5b3fce41a8fd6f9a9b1b1","source":{"kind":"arxiv","id":"1908.09492","version":1},"attestation_state":"computed","paper":{"title":"Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjin Zhu, Gang Yu, Xiangxin Zhou, Zeming Li, Zhengkai Jiang","submitted_at":"2019-08-26T06:27:01Z","abstract_excerpt":"This report presents our method which wins the nuScenes3D Detection Challenge [17] held in Workshop on Autonomous Driving(WAD, CVPR 2019). Generally, we utilize sparse 3D convolution to extract rich semantic features, which are then fed into a class-balanced multi-head network to perform 3D object detection. To handle the severe class imbalance problem inherent in the autonomous driving scenarios, we design a class-balanced sampling and augmentation strategy to generate a more balanced data distribution. Furthermore, we propose a balanced group-ing head to boost the performance for the categor"},"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":"1908.09492","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-26T06:27:01Z","cross_cats_sorted":[],"title_canon_sha256":"aaa2ccabb4b2459f584357430d2e46f366f1866af0b230baa9e97a6ae7d4f131","abstract_canon_sha256":"3c62700627a3dd8f6077c6099a4a5565beb2033efcdc3f1eee9c0655724d5b14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:40.695880Z","signature_b64":"b7mqvc1pwSUoprkaJwweMVG+8aserGqHxPPbZrtDHC5qta6Ppvr2qHyWlbvzvBdMda3r+4ZHeN9h8zg6G+oQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1920baa2ea9d818d7b9a4c49de349165eaf1700a93b5b3fce41a8fd6f9a9b1b1","last_reissued_at":"2026-07-04T23:59:40.695399Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:40.695399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjin Zhu, Gang Yu, Xiangxin Zhou, Zeming Li, Zhengkai Jiang","submitted_at":"2019-08-26T06:27:01Z","abstract_excerpt":"This report presents our method which wins the nuScenes3D Detection Challenge [17] held in Workshop on Autonomous Driving(WAD, CVPR 2019). Generally, we utilize sparse 3D convolution to extract rich semantic features, which are then fed into a class-balanced multi-head network to perform 3D object detection. To handle the severe class imbalance problem inherent in the autonomous driving scenarios, we design a class-balanced sampling and augmentation strategy to generate a more balanced data distribution. Furthermore, we propose a balanced group-ing head to boost the performance for the categor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09492","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/1908.09492/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":"1908.09492","created_at":"2026-07-04T23:59:40.695458+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.09492v1","created_at":"2026-07-04T23:59:40.695458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09492","created_at":"2026-07-04T23:59:40.695458+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEQLVIXKTWAY","created_at":"2026-07-04T23:59:40.695458+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEQLVIXKTWAY2642","created_at":"2026-07-04T23:59:40.695458+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEQLVIXK","created_at":"2026-07-04T23:59:40.695458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12981","citing_title":"Camera and LiDAR BEV Fusion for Cooperative 3D Object Detection on TUMTraf V2X","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00746","citing_title":"GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion Perception","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02924","citing_title":"ATLAS: A Large-Scale Evaluation Benchmark for Adversarial LiDAR Perception","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30983","citing_title":"Can BEV Perception Gracefully Degrade under Sensor Failures?","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17732","citing_title":"RQR3D: Reparametrizing the regression targets for BEV-based 3D object detection","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2510.26641","citing_title":"All You Need for Object Detection: From Pixels, Points, and Prompts to Next-Gen Fusion and Multimodal LLMs/VLMs in Autonomous Vehicles","ref_index":254,"is_internal_anchor":false},{"citing_arxiv_id":"1903.11027","citing_title":"nuScenes: A multimodal dataset for autonomous driving","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2112.11790","citing_title":"BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01924","citing_title":"SimPB++: Simultaneously Detecting 2D and 3D Objects from Multiple Cameras","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12918","citing_title":"Radar-Camera BEV Multi-Task Learning with Cross-Task Attention Bridge for Joint 3D Detection and Segmentation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10305","citing_title":"Class-Adaptive Cooperative Perception for Multi-Class LiDAR-based 3D Object Detection in V2X Systems","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17024","citing_title":"CAM3DNet: Comprehensively mining the multi-scale features for 3D Object Detection with Multi-View Cameras","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18476","citing_title":"SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DEQLVIXKTWAY2642JRE54NERMX","json":"https://pith.science/pith/DEQLVIXKTWAY2642JRE54NERMX.json","graph_json":"https://pith.science/api/pith-number/DEQLVIXKTWAY2642JRE54NERMX/graph.json","events_json":"https://pith.science/api/pith-number/DEQLVIXKTWAY2642JRE54NERMX/events.json","paper":"https://pith.science/paper/DEQLVIXK"},"agent_actions":{"view_html":"https://pith.science/pith/DEQLVIXKTWAY2642JRE54NERMX","download_json":"https://pith.science/pith/DEQLVIXKTWAY2642JRE54NERMX.json","view_paper":"https://pith.science/paper/DEQLVIXK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.09492&json=true","fetch_graph":"https://pith.science/api/pith-number/DEQLVIXKTWAY2642JRE54NERMX/graph.json","fetch_events":"https://pith.science/api/pith-number/DEQLVIXKTWAY2642JRE54NERMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEQLVIXKTWAY2642JRE54NERMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEQLVIXKTWAY2642JRE54NERMX/action/storage_attestation","attest_author":"https://pith.science/pith/DEQLVIXKTWAY2642JRE54NERMX/action/author_attestation","sign_citation":"https://pith.science/pith/DEQLVIXKTWAY2642JRE54NERMX/action/citation_signature","submit_replication":"https://pith.science/pith/DEQLVIXKTWAY2642JRE54NERMX/action/replication_record"}},"created_at":"2026-07-04T23:59:40.695458+00:00","updated_at":"2026-07-04T23:59:40.695458+00:00"}