{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QVXUTYRIX2RAFSHXK7YYCXAG7X","short_pith_number":"pith:QVXUTYRI","schema_version":"1.0","canonical_sha256":"856f49e228bea202c8f757f1815c06fdeb666eb227170b1f5eddef3ab7e8d931","source":{"kind":"arxiv","id":"2303.11926","version":2},"attestation_state":"computed","paper":{"title":"Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shihao Wang, Tiancai Wang, Xiangyu Zhang, Yingfei Liu, Ying Li","submitted_at":"2023-03-21T15:19:20Z","abstract_excerpt":"In this paper, we propose a long-sequence modeling framework, named StreamPETR, for multi-view 3D object detection. Built upon the sparse query design in the PETR series, we systematically develop an object-centric temporal mechanism. The model is performed in an online manner and the long-term historical information is propagated through object queries frame by frame. Besides, we introduce a motion-aware layer normalization to model the movement of the objects. StreamPETR achieves significant performance improvements only with negligible computation cost, compared to the single-frame baseline"},"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":"2303.11926","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-21T15:19:20Z","cross_cats_sorted":[],"title_canon_sha256":"521643994373d730fe8356eb3c5823df216f8429ec028a31a61e57e5c07e0b79","abstract_canon_sha256":"e62b9c2396cba53088be0d172326fc025ed31dff4cb4c9dfa621ee0acae2dd17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:21.408372Z","signature_b64":"n39DKCbEsor+78Q3/vK0sAY/b8fb2WcIW+MBq/ybapXDJWu6jKRyA9rXlwRSc/JgFvSFmj6pSfh+l22rtp2WAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"856f49e228bea202c8f757f1815c06fdeb666eb227170b1f5eddef3ab7e8d931","last_reissued_at":"2026-07-05T06:18:21.407926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:21.407926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shihao Wang, Tiancai Wang, Xiangyu Zhang, Yingfei Liu, Ying Li","submitted_at":"2023-03-21T15:19:20Z","abstract_excerpt":"In this paper, we propose a long-sequence modeling framework, named StreamPETR, for multi-view 3D object detection. Built upon the sparse query design in the PETR series, we systematically develop an object-centric temporal mechanism. The model is performed in an online manner and the long-term historical information is propagated through object queries frame by frame. Besides, we introduce a motion-aware layer normalization to model the movement of the objects. StreamPETR achieves significant performance improvements only with negligible computation cost, compared to the single-frame baseline"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11926","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/2303.11926/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":"2303.11926","created_at":"2026-07-05T06:18:21.407990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11926v2","created_at":"2026-07-05T06:18:21.407990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11926","created_at":"2026-07-05T06:18:21.407990+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVXUTYRIX2RA","created_at":"2026-07-05T06:18:21.407990+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVXUTYRIX2RAFSHX","created_at":"2026-07-05T06:18:21.407990+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVXUTYRI","created_at":"2026-07-05T06:18:21.407990+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29935","citing_title":"CityGen: Structure-Guided City-Style Synthesis for Cross-City Autonomous Driving","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13243","citing_title":"VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13571","citing_title":"Radar-Informed 3D Multi-Object Tracking under Adverse Conditions","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVXUTYRIX2RAFSHXK7YYCXAG7X","json":"https://pith.science/pith/QVXUTYRIX2RAFSHXK7YYCXAG7X.json","graph_json":"https://pith.science/api/pith-number/QVXUTYRIX2RAFSHXK7YYCXAG7X/graph.json","events_json":"https://pith.science/api/pith-number/QVXUTYRIX2RAFSHXK7YYCXAG7X/events.json","paper":"https://pith.science/paper/QVXUTYRI"},"agent_actions":{"view_html":"https://pith.science/pith/QVXUTYRIX2RAFSHXK7YYCXAG7X","download_json":"https://pith.science/pith/QVXUTYRIX2RAFSHXK7YYCXAG7X.json","view_paper":"https://pith.science/paper/QVXUTYRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11926&json=true","fetch_graph":"https://pith.science/api/pith-number/QVXUTYRIX2RAFSHXK7YYCXAG7X/graph.json","fetch_events":"https://pith.science/api/pith-number/QVXUTYRIX2RAFSHXK7YYCXAG7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVXUTYRIX2RAFSHXK7YYCXAG7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVXUTYRIX2RAFSHXK7YYCXAG7X/action/storage_attestation","attest_author":"https://pith.science/pith/QVXUTYRIX2RAFSHXK7YYCXAG7X/action/author_attestation","sign_citation":"https://pith.science/pith/QVXUTYRIX2RAFSHXK7YYCXAG7X/action/citation_signature","submit_replication":"https://pith.science/pith/QVXUTYRIX2RAFSHXK7YYCXAG7X/action/replication_record"}},"created_at":"2026-07-05T06:18:21.407990+00:00","updated_at":"2026-07-05T06:18:21.407990+00:00"}