{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FLMVLKF4MMVXCYWFV7MXX4FYPN","short_pith_number":"pith:FLMVLKF4","schema_version":"1.0","canonical_sha256":"2ad955a8bc632b7162c5afd97bf0b87b6ba31153c430d5da580e6b3ef51a1bd8","source":{"kind":"arxiv","id":"2212.07849","version":1},"attestation_state":"computed","paper":{"title":"DETR4D: Direct Multi-View 3D Object Detection with Sparse Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqing Zhou, Gongjie Zhang, Shijian Lu, Zhipeng Luo","submitted_at":"2022-12-15T14:18:47Z","abstract_excerpt":"3D object detection with surround-view images is an essential task for autonomous driving. In this work, we propose DETR4D, a Transformer-based framework that explores sparse attention and direct feature query for 3D object detection in multi-view images. We design a novel projective cross-attention mechanism for query-image interaction to address the limitations of existing methods in terms of geometric cue exploitation and information loss for cross-view objects. In addition, we introduce a heatmap generation technique that bridges 3D and 2D spaces efficiently via query initialization. Furth"},"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":"2212.07849","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-15T14:18:47Z","cross_cats_sorted":[],"title_canon_sha256":"9d35d28e9c20512cd924266a981ae37d69ded9317e083a830b3525e3b7bc08ce","abstract_canon_sha256":"326c293c76d0e275e2ddcd7be775f6f9c131c9ee6558d1aa6a87e2f8fe8b99b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:38.444696Z","signature_b64":"BpAwtL8asmHNHlPmiiAWtxDaLK7JfEU1TX0d9Fp3yj/fbJDGIDaYfEvsFxgyx3kBxTi+k3VcQnWoyh7gG4VnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ad955a8bc632b7162c5afd97bf0b87b6ba31153c430d5da580e6b3ef51a1bd8","last_reissued_at":"2026-07-05T05:25:38.444250Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:38.444250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DETR4D: Direct Multi-View 3D Object Detection with Sparse Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqing Zhou, Gongjie Zhang, Shijian Lu, Zhipeng Luo","submitted_at":"2022-12-15T14:18:47Z","abstract_excerpt":"3D object detection with surround-view images is an essential task for autonomous driving. In this work, we propose DETR4D, a Transformer-based framework that explores sparse attention and direct feature query for 3D object detection in multi-view images. We design a novel projective cross-attention mechanism for query-image interaction to address the limitations of existing methods in terms of geometric cue exploitation and information loss for cross-view objects. In addition, we introduce a heatmap generation technique that bridges 3D and 2D spaces efficiently via query initialization. Furth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07849","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/2212.07849/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":"2212.07849","created_at":"2026-07-05T05:25:38.444308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.07849v1","created_at":"2026-07-05T05:25:38.444308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07849","created_at":"2026-07-05T05:25:38.444308+00:00"},{"alias_kind":"pith_short_12","alias_value":"FLMVLKF4MMVX","created_at":"2026-07-05T05:25:38.444308+00:00"},{"alias_kind":"pith_short_16","alias_value":"FLMVLKF4MMVXCYWF","created_at":"2026-07-05T05:25:38.444308+00:00"},{"alias_kind":"pith_short_8","alias_value":"FLMVLKF4","created_at":"2026-07-05T05:25:38.444308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01924","citing_title":"SimPB++: Simultaneously Detecting 2D and 3D Objects from Multiple Cameras","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FLMVLKF4MMVXCYWFV7MXX4FYPN","json":"https://pith.science/pith/FLMVLKF4MMVXCYWFV7MXX4FYPN.json","graph_json":"https://pith.science/api/pith-number/FLMVLKF4MMVXCYWFV7MXX4FYPN/graph.json","events_json":"https://pith.science/api/pith-number/FLMVLKF4MMVXCYWFV7MXX4FYPN/events.json","paper":"https://pith.science/paper/FLMVLKF4"},"agent_actions":{"view_html":"https://pith.science/pith/FLMVLKF4MMVXCYWFV7MXX4FYPN","download_json":"https://pith.science/pith/FLMVLKF4MMVXCYWFV7MXX4FYPN.json","view_paper":"https://pith.science/paper/FLMVLKF4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.07849&json=true","fetch_graph":"https://pith.science/api/pith-number/FLMVLKF4MMVXCYWFV7MXX4FYPN/graph.json","fetch_events":"https://pith.science/api/pith-number/FLMVLKF4MMVXCYWFV7MXX4FYPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FLMVLKF4MMVXCYWFV7MXX4FYPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FLMVLKF4MMVXCYWFV7MXX4FYPN/action/storage_attestation","attest_author":"https://pith.science/pith/FLMVLKF4MMVXCYWFV7MXX4FYPN/action/author_attestation","sign_citation":"https://pith.science/pith/FLMVLKF4MMVXCYWFV7MXX4FYPN/action/citation_signature","submit_replication":"https://pith.science/pith/FLMVLKF4MMVXCYWFV7MXX4FYPN/action/replication_record"}},"created_at":"2026-07-05T05:25:38.444308+00:00","updated_at":"2026-07-05T05:25:38.444308+00:00"}