{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VTWNUPGZ2KJNSLFVSYBF5XXCFR","short_pith_number":"pith:VTWNUPGZ","schema_version":"1.0","canonical_sha256":"acecda3cd9d292d92cb596025edee22c4a105fe37fd37bde3dd56769a758e4c4","source":{"kind":"arxiv","id":"2301.01283","version":3},"attestation_state":"computed","paper":{"title":"Cross Modal Transformer: Towards Fast and Robust 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Jia, Jianjian Sun, Junjie Yan, Shuailin Li, Tiancai Wang, Xiangyu Zhang, Yingfei Liu","submitted_at":"2023-01-03T18:36:52Z","abstract_excerpt":"In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the image and point clouds tokens as inputs and directly outputs accurate 3D bounding boxes. The spatial alignment of multi-modal tokens is performed by encoding the 3D points into multi-modal features. The core design of CMT is quite simple while its performance is impressive. It achieves 74.1\\% NDS (state-of-the-art with single model) on nuScenes test set while maintaining fast inference speed. Moreover, CMT has a strong"},"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":"2301.01283","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-03T18:36:52Z","cross_cats_sorted":[],"title_canon_sha256":"65eed3b96a33005748b26e989a7e83ff9ea50215fa6d62084718efd4f4dece2f","abstract_canon_sha256":"4d43bfefd7eee6e5e80b89591a2ef8e2eac71b5d3d56de6507b95cb0f207d9bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:21.473451Z","signature_b64":"IhhRdLayVwgv7KGtDx2paAaLstAIrrYXbmqwwM+/4mqiDR9Mpwz4YJvWzlw1QIPWknYKosP2EOOt5HnOXfd3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acecda3cd9d292d92cb596025edee22c4a105fe37fd37bde3dd56769a758e4c4","last_reissued_at":"2026-07-05T06:51:21.472902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:21.472902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross Modal Transformer: Towards Fast and Robust 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Jia, Jianjian Sun, Junjie Yan, Shuailin Li, Tiancai Wang, Xiangyu Zhang, Yingfei Liu","submitted_at":"2023-01-03T18:36:52Z","abstract_excerpt":"In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the image and point clouds tokens as inputs and directly outputs accurate 3D bounding boxes. The spatial alignment of multi-modal tokens is performed by encoding the 3D points into multi-modal features. The core design of CMT is quite simple while its performance is impressive. It achieves 74.1\\% NDS (state-of-the-art with single model) on nuScenes test set while maintaining fast inference speed. Moreover, CMT has a strong"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01283","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/2301.01283/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":"2301.01283","created_at":"2026-07-05T06:51:21.472963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.01283v3","created_at":"2026-07-05T06:51:21.472963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.01283","created_at":"2026-07-05T06:51:21.472963+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTWNUPGZ2KJN","created_at":"2026-07-05T06:51:21.472963+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTWNUPGZ2KJNSLFV","created_at":"2026-07-05T06:51:21.472963+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTWNUPGZ","created_at":"2026-07-05T06:51:21.472963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09899","citing_title":"Hyperbolic Distillation: Geometry-Guided Cross-Modal Transfer for Robust 3D Object Detection","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05405","citing_title":"Weather-Conditioned Branch Routing for Robust LiDAR-Radar 3D Object Detection","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VTWNUPGZ2KJNSLFVSYBF5XXCFR","json":"https://pith.science/pith/VTWNUPGZ2KJNSLFVSYBF5XXCFR.json","graph_json":"https://pith.science/api/pith-number/VTWNUPGZ2KJNSLFVSYBF5XXCFR/graph.json","events_json":"https://pith.science/api/pith-number/VTWNUPGZ2KJNSLFVSYBF5XXCFR/events.json","paper":"https://pith.science/paper/VTWNUPGZ"},"agent_actions":{"view_html":"https://pith.science/pith/VTWNUPGZ2KJNSLFVSYBF5XXCFR","download_json":"https://pith.science/pith/VTWNUPGZ2KJNSLFVSYBF5XXCFR.json","view_paper":"https://pith.science/paper/VTWNUPGZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.01283&json=true","fetch_graph":"https://pith.science/api/pith-number/VTWNUPGZ2KJNSLFVSYBF5XXCFR/graph.json","fetch_events":"https://pith.science/api/pith-number/VTWNUPGZ2KJNSLFVSYBF5XXCFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTWNUPGZ2KJNSLFVSYBF5XXCFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTWNUPGZ2KJNSLFVSYBF5XXCFR/action/storage_attestation","attest_author":"https://pith.science/pith/VTWNUPGZ2KJNSLFVSYBF5XXCFR/action/author_attestation","sign_citation":"https://pith.science/pith/VTWNUPGZ2KJNSLFVSYBF5XXCFR/action/citation_signature","submit_replication":"https://pith.science/pith/VTWNUPGZ2KJNSLFVSYBF5XXCFR/action/replication_record"}},"created_at":"2026-07-05T06:51:21.472963+00:00","updated_at":"2026-07-05T06:51:21.472963+00:00"}