{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DXV3MGC3JZCYPLQGUTCBEQFLDL","short_pith_number":"pith:DXV3MGC3","schema_version":"1.0","canonical_sha256":"1debb6185b4e4587ae06a4c41240ab1acb2871aa4982e26d1ce174e725f68e10","source":{"kind":"arxiv","id":"2406.17654","version":2},"attestation_state":"computed","paper":{"title":"MDHA: Multi-Scale Deformable Transformer with Hybrid Anchors for Multi-View 3D Object Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Junn Yong Loo, Michelle Adeline, Vishnu Monn Baskaran","submitted_at":"2024-06-25T15:46:39Z","abstract_excerpt":"Multi-view 3D object detection is a crucial component of autonomous driving systems. Contemporary query-based methods primarily depend either on dataset-specific initialization of 3D anchors, introducing bias, or utilize dense attention mechanisms, which are computationally inefficient and unscalable. To overcome these issues, we present MDHA, a novel sparse query-based framework, which constructs adaptive 3D output proposals using hybrid anchors from multi-view, multi-scale image input. Fixed 2D anchors are combined with depth predictions to form 2.5D anchors, which are projected to obtain 3D"},"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":"2406.17654","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-25T15:46:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"34856d4dbd78a73fc4882dcdd6c0a192b5b6817e4bc8a6a752317c3aae606a94","abstract_canon_sha256":"ae0329be8c0a7a27eaac3be455b3d0ce913f4efacb0c1ebf49b512d5bc9df57d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:34.045767Z","signature_b64":"j8b9YwlEGYYmcibctW6goKigrhQyHQXNVU7iPxX+FsJzIHfF1+6zmH3QgGrARAPc4mt0x+yxOZtnxJbbgtHUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1debb6185b4e4587ae06a4c41240ab1acb2871aa4982e26d1ce174e725f68e10","last_reissued_at":"2026-07-05T09:33:34.045270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:34.045270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MDHA: Multi-Scale Deformable Transformer with Hybrid Anchors for Multi-View 3D Object Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Junn Yong Loo, Michelle Adeline, Vishnu Monn Baskaran","submitted_at":"2024-06-25T15:46:39Z","abstract_excerpt":"Multi-view 3D object detection is a crucial component of autonomous driving systems. Contemporary query-based methods primarily depend either on dataset-specific initialization of 3D anchors, introducing bias, or utilize dense attention mechanisms, which are computationally inefficient and unscalable. To overcome these issues, we present MDHA, a novel sparse query-based framework, which constructs adaptive 3D output proposals using hybrid anchors from multi-view, multi-scale image input. Fixed 2D anchors are combined with depth predictions to form 2.5D anchors, which are projected to obtain 3D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17654","kind":"arxiv","version":2},"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/2406.17654/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":"2406.17654","created_at":"2026-07-05T09:33:34.045327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17654v2","created_at":"2026-07-05T09:33:34.045327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17654","created_at":"2026-07-05T09:33:34.045327+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXV3MGC3JZCY","created_at":"2026-07-05T09:33:34.045327+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXV3MGC3JZCYPLQG","created_at":"2026-07-05T09:33:34.045327+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXV3MGC3","created_at":"2026-07-05T09:33:34.045327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXV3MGC3JZCYPLQGUTCBEQFLDL","json":"https://pith.science/pith/DXV3MGC3JZCYPLQGUTCBEQFLDL.json","graph_json":"https://pith.science/api/pith-number/DXV3MGC3JZCYPLQGUTCBEQFLDL/graph.json","events_json":"https://pith.science/api/pith-number/DXV3MGC3JZCYPLQGUTCBEQFLDL/events.json","paper":"https://pith.science/paper/DXV3MGC3"},"agent_actions":{"view_html":"https://pith.science/pith/DXV3MGC3JZCYPLQGUTCBEQFLDL","download_json":"https://pith.science/pith/DXV3MGC3JZCYPLQGUTCBEQFLDL.json","view_paper":"https://pith.science/paper/DXV3MGC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17654&json=true","fetch_graph":"https://pith.science/api/pith-number/DXV3MGC3JZCYPLQGUTCBEQFLDL/graph.json","fetch_events":"https://pith.science/api/pith-number/DXV3MGC3JZCYPLQGUTCBEQFLDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXV3MGC3JZCYPLQGUTCBEQFLDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXV3MGC3JZCYPLQGUTCBEQFLDL/action/storage_attestation","attest_author":"https://pith.science/pith/DXV3MGC3JZCYPLQGUTCBEQFLDL/action/author_attestation","sign_citation":"https://pith.science/pith/DXV3MGC3JZCYPLQGUTCBEQFLDL/action/citation_signature","submit_replication":"https://pith.science/pith/DXV3MGC3JZCYPLQGUTCBEQFLDL/action/replication_record"}},"created_at":"2026-07-05T09:33:34.045327+00:00","updated_at":"2026-07-05T09:33:34.045327+00:00"}