{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6CQWBFKN63WT2CGIQGOMIWM6QN","short_pith_number":"pith:6CQWBFKN","schema_version":"1.0","canonical_sha256":"f0a160954df6ed3d08c8819cc4599e835abe1694eb8b1d718c0ebe141e423963","source":{"kind":"arxiv","id":"2209.13507","version":3},"attestation_state":"computed","paper":{"title":"CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Ching-Yu Tseng, Hsin-Ying Lee, Tsung-Han Wu, Wen-Chin Chen, Winston H. Hsu, Yi-Rong Chen","submitted_at":"2022-09-27T16:23:12Z","abstract_excerpt":"To achieve accurate 3D object detection at a low cost for autonomous driving, many multi-camera methods have been proposed and solved the occlusion problem of monocular approaches. However, due to the lack of accurate estimated depth, existing multi-camera methods often generate multiple bounding boxes along a ray of depth direction for difficult small objects such as pedestrians, resulting in an extremely low recall. Furthermore, directly applying depth prediction modules to existing multi-camera methods, generally composed of large network architectures, cannot meet the real-time requirement"},"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":"2209.13507","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-27T16:23:12Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"d7f72dd756a9f12bda45d6fef0e57ca860d0d271093e06bc8a1a9338c7b5e97c","abstract_canon_sha256":"587064cc78eabcd72adefb01a969deb8adfe1edb07aa02b195ffb459cb344bf9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:29.075442Z","signature_b64":"MpKYffWBY3TgOMWxp3k0PX6QmSsn6/dgNzuix4Wj8ViySsKSLcxPKeFRcV1rSqAaBlwQoaEeTzOYDBzAvSTyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0a160954df6ed3d08c8819cc4599e835abe1694eb8b1d718c0ebe141e423963","last_reissued_at":"2026-07-05T05:38:29.074956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:29.074956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Ching-Yu Tseng, Hsin-Ying Lee, Tsung-Han Wu, Wen-Chin Chen, Winston H. Hsu, Yi-Rong Chen","submitted_at":"2022-09-27T16:23:12Z","abstract_excerpt":"To achieve accurate 3D object detection at a low cost for autonomous driving, many multi-camera methods have been proposed and solved the occlusion problem of monocular approaches. However, due to the lack of accurate estimated depth, existing multi-camera methods often generate multiple bounding boxes along a ray of depth direction for difficult small objects such as pedestrians, resulting in an extremely low recall. Furthermore, directly applying depth prediction modules to existing multi-camera methods, generally composed of large network architectures, cannot meet the real-time requirement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.13507","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/2209.13507/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":"2209.13507","created_at":"2026-07-05T05:38:29.075011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.13507v3","created_at":"2026-07-05T05:38:29.075011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.13507","created_at":"2026-07-05T05:38:29.075011+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CQWBFKN63WT","created_at":"2026-07-05T05:38:29.075011+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CQWBFKN63WT2CGI","created_at":"2026-07-05T05:38:29.075011+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CQWBFKN","created_at":"2026-07-05T05:38:29.075011+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20063","citing_title":"OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CQWBFKN63WT2CGIQGOMIWM6QN","json":"https://pith.science/pith/6CQWBFKN63WT2CGIQGOMIWM6QN.json","graph_json":"https://pith.science/api/pith-number/6CQWBFKN63WT2CGIQGOMIWM6QN/graph.json","events_json":"https://pith.science/api/pith-number/6CQWBFKN63WT2CGIQGOMIWM6QN/events.json","paper":"https://pith.science/paper/6CQWBFKN"},"agent_actions":{"view_html":"https://pith.science/pith/6CQWBFKN63WT2CGIQGOMIWM6QN","download_json":"https://pith.science/pith/6CQWBFKN63WT2CGIQGOMIWM6QN.json","view_paper":"https://pith.science/paper/6CQWBFKN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.13507&json=true","fetch_graph":"https://pith.science/api/pith-number/6CQWBFKN63WT2CGIQGOMIWM6QN/graph.json","fetch_events":"https://pith.science/api/pith-number/6CQWBFKN63WT2CGIQGOMIWM6QN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CQWBFKN63WT2CGIQGOMIWM6QN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CQWBFKN63WT2CGIQGOMIWM6QN/action/storage_attestation","attest_author":"https://pith.science/pith/6CQWBFKN63WT2CGIQGOMIWM6QN/action/author_attestation","sign_citation":"https://pith.science/pith/6CQWBFKN63WT2CGIQGOMIWM6QN/action/citation_signature","submit_replication":"https://pith.science/pith/6CQWBFKN63WT2CGIQGOMIWM6QN/action/replication_record"}},"created_at":"2026-07-05T05:38:29.075011+00:00","updated_at":"2026-07-05T05:38:29.075011+00:00"}