{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JZOBU3B6QBYPX3IKTK242YSZIT","short_pith_number":"pith:JZOBU3B6","schema_version":"1.0","canonical_sha256":"4e5c1a6c3e8070fbed0a9ab5cd625944fb3e38980c0d0b55356f6c19b8b7fdf2","source":{"kind":"arxiv","id":"2207.12716","version":1},"attestation_state":"computed","paper":{"title":"MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbones","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Chenming Zhu, Qing Lian, Tai Wang, Wenwei Zhang, Xinge Zhu","submitted_at":"2022-07-26T08:10:29Z","abstract_excerpt":"In this technical report, we present our solution, dubbed MV-FCOS3D++, for the Camera-Only 3D Detection track in Waymo Open Dataset Challenge 2022. For multi-view camera-only 3D detection, methods based on bird-eye-view or 3D geometric representations can leverage the stereo cues from overlapped regions between adjacent views and directly perform 3D detection without hand-crafted post-processing. However, it lacks direct semantic supervision for 2D backbones, which can be complemented by pretraining simple monocular-based detectors. Our solution is a multi-view framework for 4D detection follo"},"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":"2207.12716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-26T08:10:29Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"b222d2ac7559b0ac0394e56bd2bae36238c0c7bf67e232e6426f3168ea7aafee","abstract_canon_sha256":"de99e9d7b753a42c6009c2562f9851cada1ce610cda35f609c439e0f23b5211a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:43:25.488901Z","signature_b64":"h8GwkoGD9pPj8or5itRwxN3hePFA3IaQhty56ImWqxmdNK2vSnmmArU7Q9H/6FEYn8NoAgH2O+BVHIE579MJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e5c1a6c3e8070fbed0a9ab5cd625944fb3e38980c0d0b55356f6c19b8b7fdf2","last_reissued_at":"2026-07-05T04:43:25.488574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:43:25.488574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbones","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Chenming Zhu, Qing Lian, Tai Wang, Wenwei Zhang, Xinge Zhu","submitted_at":"2022-07-26T08:10:29Z","abstract_excerpt":"In this technical report, we present our solution, dubbed MV-FCOS3D++, for the Camera-Only 3D Detection track in Waymo Open Dataset Challenge 2022. For multi-view camera-only 3D detection, methods based on bird-eye-view or 3D geometric representations can leverage the stereo cues from overlapped regions between adjacent views and directly perform 3D detection without hand-crafted post-processing. However, it lacks direct semantic supervision for 2D backbones, which can be complemented by pretraining simple monocular-based detectors. Our solution is a multi-view framework for 4D detection follo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.12716","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/2207.12716/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":"2207.12716","created_at":"2026-07-05T04:43:25.488619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.12716v1","created_at":"2026-07-05T04:43:25.488619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.12716","created_at":"2026-07-05T04:43:25.488619+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZOBU3B6QBYP","created_at":"2026-07-05T04:43:25.488619+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZOBU3B6QBYPX3IK","created_at":"2026-07-05T04:43:25.488619+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZOBU3B6","created_at":"2026-07-05T04:43:25.488619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17024","citing_title":"CAM3DNet: Comprehensively mining the multi-scale features for 3D Object Detection with Multi-View Cameras","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JZOBU3B6QBYPX3IKTK242YSZIT","json":"https://pith.science/pith/JZOBU3B6QBYPX3IKTK242YSZIT.json","graph_json":"https://pith.science/api/pith-number/JZOBU3B6QBYPX3IKTK242YSZIT/graph.json","events_json":"https://pith.science/api/pith-number/JZOBU3B6QBYPX3IKTK242YSZIT/events.json","paper":"https://pith.science/paper/JZOBU3B6"},"agent_actions":{"view_html":"https://pith.science/pith/JZOBU3B6QBYPX3IKTK242YSZIT","download_json":"https://pith.science/pith/JZOBU3B6QBYPX3IKTK242YSZIT.json","view_paper":"https://pith.science/paper/JZOBU3B6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.12716&json=true","fetch_graph":"https://pith.science/api/pith-number/JZOBU3B6QBYPX3IKTK242YSZIT/graph.json","fetch_events":"https://pith.science/api/pith-number/JZOBU3B6QBYPX3IKTK242YSZIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZOBU3B6QBYPX3IKTK242YSZIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZOBU3B6QBYPX3IKTK242YSZIT/action/storage_attestation","attest_author":"https://pith.science/pith/JZOBU3B6QBYPX3IKTK242YSZIT/action/author_attestation","sign_citation":"https://pith.science/pith/JZOBU3B6QBYPX3IKTK242YSZIT/action/citation_signature","submit_replication":"https://pith.science/pith/JZOBU3B6QBYPX3IKTK242YSZIT/action/replication_record"}},"created_at":"2026-07-05T04:43:25.488619+00:00","updated_at":"2026-07-05T04:43:25.488619+00:00"}