{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3TOESIYIYGRQVZCYWSQSMF6VWA","short_pith_number":"pith:3TOESIYI","schema_version":"1.0","canonical_sha256":"dcdc492308c1a30ae458b4a12617d5b016e6e5099e4a3135d2cfc66276333703","source":{"kind":"arxiv","id":"2210.02443","version":1},"attestation_state":"computed","paper":{"title":"Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chenfeng Xu, Jinhyung Park, Kris Kitani, Kurt Keutzer, Masayoshi Tomizuka, Shijia Yang, Wei Zhan","submitted_at":"2022-10-05T17:59:51Z","abstract_excerpt":"While recent camera-only 3D detection methods leverage multiple timesteps, the limited history they use significantly hampers the extent to which temporal fusion can improve object perception. Observing that existing works' fusion of multi-frame images are instances of temporal stereo matching, we find that performance is hindered by the interplay between 1) the low granularity of matching resolution and 2) the sub-optimal multi-view setup produced by limited history usage. Our theoretical and empirical analysis demonstrates that the optimal temporal difference between views varies significant"},"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":"2210.02443","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-05T17:59:51Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"ad2423f1196829920af7cad807a3831d9e33b3bea8123e8145fb81a67c555aad","abstract_canon_sha256":"125103bb3aa55acd7a1de1821769c84df47592d15b0f1b03260907f434cf9e5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:48.029833Z","signature_b64":"oXwxRUIqMYIG9RsBUwuMcYyOXr+YAOY9ZzOcUWCw/z2pjo6jjRwh8FYQcP2TaV6RUWPNbblnJq6AtK4S2Dl+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcdc492308c1a30ae458b4a12617d5b016e6e5099e4a3135d2cfc66276333703","last_reissued_at":"2026-07-05T05:03:48.029266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:48.029266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chenfeng Xu, Jinhyung Park, Kris Kitani, Kurt Keutzer, Masayoshi Tomizuka, Shijia Yang, Wei Zhan","submitted_at":"2022-10-05T17:59:51Z","abstract_excerpt":"While recent camera-only 3D detection methods leverage multiple timesteps, the limited history they use significantly hampers the extent to which temporal fusion can improve object perception. Observing that existing works' fusion of multi-frame images are instances of temporal stereo matching, we find that performance is hindered by the interplay between 1) the low granularity of matching resolution and 2) the sub-optimal multi-view setup produced by limited history usage. Our theoretical and empirical analysis demonstrates that the optimal temporal difference between views varies significant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02443","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/2210.02443/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":"2210.02443","created_at":"2026-07-05T05:03:48.029347+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.02443v1","created_at":"2026-07-05T05:03:48.029347+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02443","created_at":"2026-07-05T05:03:48.029347+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TOESIYIYGRQ","created_at":"2026-07-05T05:03:48.029347+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TOESIYIYGRQVZCY","created_at":"2026-07-05T05:03:48.029347+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TOESIYI","created_at":"2026-07-05T05:03:48.029347+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.17732","citing_title":"RQR3D: Reparametrizing the regression targets for BEV-based 3D object detection","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2406.08481","citing_title":"Enhancing End-to-End Autonomous Driving with Latent World Model","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24044","citing_title":"CLLAP: Contrastive Learning-based LiDAR-Augmented Pretraining for Enhanced Radar-Camera Fusion","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13586","citing_title":"Efficient Multi-View 3D Object Detection by Dynamic Token Selection and Fine-Tuning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17024","citing_title":"CAM3DNet: Comprehensively mining the multi-scale features for 3D Object Detection with Multi-View Cameras","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18476","citing_title":"SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3TOESIYIYGRQVZCYWSQSMF6VWA","json":"https://pith.science/pith/3TOESIYIYGRQVZCYWSQSMF6VWA.json","graph_json":"https://pith.science/api/pith-number/3TOESIYIYGRQVZCYWSQSMF6VWA/graph.json","events_json":"https://pith.science/api/pith-number/3TOESIYIYGRQVZCYWSQSMF6VWA/events.json","paper":"https://pith.science/paper/3TOESIYI"},"agent_actions":{"view_html":"https://pith.science/pith/3TOESIYIYGRQVZCYWSQSMF6VWA","download_json":"https://pith.science/pith/3TOESIYIYGRQVZCYWSQSMF6VWA.json","view_paper":"https://pith.science/paper/3TOESIYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.02443&json=true","fetch_graph":"https://pith.science/api/pith-number/3TOESIYIYGRQVZCYWSQSMF6VWA/graph.json","fetch_events":"https://pith.science/api/pith-number/3TOESIYIYGRQVZCYWSQSMF6VWA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TOESIYIYGRQVZCYWSQSMF6VWA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TOESIYIYGRQVZCYWSQSMF6VWA/action/storage_attestation","attest_author":"https://pith.science/pith/3TOESIYIYGRQVZCYWSQSMF6VWA/action/author_attestation","sign_citation":"https://pith.science/pith/3TOESIYIYGRQVZCYWSQSMF6VWA/action/citation_signature","submit_replication":"https://pith.science/pith/3TOESIYIYGRQVZCYWSQSMF6VWA/action/replication_record"}},"created_at":"2026-07-05T05:03:48.029347+00:00","updated_at":"2026-07-05T05:03:48.029347+00:00"}