{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LD6PNGFRUUQQ4JAA4BL2VUXHD7","short_pith_number":"pith:LD6PNGFR","schema_version":"1.0","canonical_sha256":"58fcf698b1a5210e2400e057aad2e71fee47fad60530563ac8713aae3158afb3","source":{"kind":"arxiv","id":"2203.17054","version":3},"attestation_state":"computed","paper":{"title":"BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guan Huang, Junjie Huang","submitted_at":"2022-03-31T14:21:19Z","abstract_excerpt":"Single frame data contains finite information which limits the performance of the existing vision-based multi-camera 3D object detection paradigms. For fundamentally pushing the performance boundary in this area, a novel paradigm dubbed BEVDet4D is proposed to lift the scalable BEVDet paradigm from the spatial-only 3D space to the spatial-temporal 4D space. We upgrade the naive BEVDet framework with a few modifications just for fusing the feature from the previous frame with the corresponding one in the current frame. In this way, with negligible additional computing budget, we enable BEVDet4D"},"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":"2203.17054","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-31T14:21:19Z","cross_cats_sorted":[],"title_canon_sha256":"5c3cba3e675ad39db7d9384dc41e44b3d87e608867208f5533dbcb4d7d675934","abstract_canon_sha256":"924af262f3e63f060332b0e06e2146b7fdd9fb1069acde2fa3b2c16fac3a586e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:15.953656Z","signature_b64":"7mKsrJsK+h4CRIN/tEneLk7Z032/s8PBHoojF2uPV97asnCS+w4C2u/qDFy7bcsYO58rh79JkMoN/eSjqRfTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58fcf698b1a5210e2400e057aad2e71fee47fad60530563ac8713aae3158afb3","last_reissued_at":"2026-07-05T04:32:15.953120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:15.953120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guan Huang, Junjie Huang","submitted_at":"2022-03-31T14:21:19Z","abstract_excerpt":"Single frame data contains finite information which limits the performance of the existing vision-based multi-camera 3D object detection paradigms. For fundamentally pushing the performance boundary in this area, a novel paradigm dubbed BEVDet4D is proposed to lift the scalable BEVDet paradigm from the spatial-only 3D space to the spatial-temporal 4D space. We upgrade the naive BEVDet framework with a few modifications just for fusing the feature from the previous frame with the corresponding one in the current frame. In this way, with negligible additional computing budget, we enable BEVDet4D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.17054","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/2203.17054/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":"2203.17054","created_at":"2026-07-05T04:32:15.953186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.17054v3","created_at":"2026-07-05T04:32:15.953186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.17054","created_at":"2026-07-05T04:32:15.953186+00:00"},{"alias_kind":"pith_short_12","alias_value":"LD6PNGFRUUQQ","created_at":"2026-07-05T04:32:15.953186+00:00"},{"alias_kind":"pith_short_16","alias_value":"LD6PNGFRUUQQ4JAA","created_at":"2026-07-05T04:32:15.953186+00:00"},{"alias_kind":"pith_short_8","alias_value":"LD6PNGFR","created_at":"2026-07-05T04:32:15.953186+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08680","citing_title":"Distortion-Aware PETR for BEV Object Detection with Mixed Pinhole-Fisheye Cameras","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00746","citing_title":"GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion Perception","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30754","citing_title":"Streaming Gaussian Encoding for 4D Panoptic Occupancy Tracking","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12218","citing_title":"Learning Ego-Centric BEV Representations from a Perspective-Privileged View: Cross-View Supervision for Online HD Map Construction","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2512.08237","citing_title":"Fast-BEV++: Fast by Algorithm, Deployable by Design","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17732","citing_title":"RQR3D: Reparametrizing the regression targets for BEV-based 3D object detection","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02930","citing_title":"BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12218","citing_title":"Learning Ego-Centric BEV Representations from a Perspective-Privileged View: Cross-View Supervision for Online HD Map Construction","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01924","citing_title":"SimPB++: Simultaneously Detecting 2D and 3D Objects from Multiple Cameras","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04797","citing_title":"Multi-Modal Sensor Fusion using Hybrid Attention for Autonomous Driving","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05449","citing_title":"Not All Agents Matter: From Global Attention Dilution to Risk-Prioritized Game Planning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14563","citing_title":"Revisiting Token Compression for Accelerating ViT-based Sparse Multi-View 3D Object Detectors","ref_index":15,"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":6,"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":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LD6PNGFRUUQQ4JAA4BL2VUXHD7","json":"https://pith.science/pith/LD6PNGFRUUQQ4JAA4BL2VUXHD7.json","graph_json":"https://pith.science/api/pith-number/LD6PNGFRUUQQ4JAA4BL2VUXHD7/graph.json","events_json":"https://pith.science/api/pith-number/LD6PNGFRUUQQ4JAA4BL2VUXHD7/events.json","paper":"https://pith.science/paper/LD6PNGFR"},"agent_actions":{"view_html":"https://pith.science/pith/LD6PNGFRUUQQ4JAA4BL2VUXHD7","download_json":"https://pith.science/pith/LD6PNGFRUUQQ4JAA4BL2VUXHD7.json","view_paper":"https://pith.science/paper/LD6PNGFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.17054&json=true","fetch_graph":"https://pith.science/api/pith-number/LD6PNGFRUUQQ4JAA4BL2VUXHD7/graph.json","fetch_events":"https://pith.science/api/pith-number/LD6PNGFRUUQQ4JAA4BL2VUXHD7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LD6PNGFRUUQQ4JAA4BL2VUXHD7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LD6PNGFRUUQQ4JAA4BL2VUXHD7/action/storage_attestation","attest_author":"https://pith.science/pith/LD6PNGFRUUQQ4JAA4BL2VUXHD7/action/author_attestation","sign_citation":"https://pith.science/pith/LD6PNGFRUUQQ4JAA4BL2VUXHD7/action/citation_signature","submit_replication":"https://pith.science/pith/LD6PNGFRUUQQ4JAA4BL2VUXHD7/action/replication_record"}},"created_at":"2026-07-05T04:32:15.953186+00:00","updated_at":"2026-07-05T04:32:15.953186+00:00"}