{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D5QS42NTGCPNNAKETMG5HFE3SB","short_pith_number":"pith:D5QS42NT","schema_version":"1.0","canonical_sha256":"1f612e69b3309ed681449b0dd3949b90789a93807db724489aa032a9cab23c92","source":{"kind":"arxiv","id":"2412.00692","version":3},"attestation_state":"computed","paper":{"title":"MCBLT: Multi-Camera Multi-Object 3D Tracking in Long Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjamin Missaoui, Cheng-Yen Yang, Laura Leal-Taix\\'e, Orcun Cetintas, Sameer Satish Pusegaonkar, Sujit Biswas, Tim Meinhardt, Yizhou Wang, Zheng Tang","submitted_at":"2024-12-01T06:18:06Z","abstract_excerpt":"Object perception from multi-view cameras is crucial for intelligent systems, particularly in indoor environments, e.g., warehouses, retail stores, and hospitals. Most traditional multi-target multi-camera (MTMC) detection and tracking methods rely on 2D object detection, single-view multi-object tracking (MOT), and cross-view re-identification (ReID) techniques, without properly handling important 3D information by multi-view image aggregation. In this paper, we propose a 3D object detection and tracking framework, named MCBLT, which first aggregates multi-view images with necessary camera ca"},"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":"2412.00692","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-01T06:18:06Z","cross_cats_sorted":[],"title_canon_sha256":"b5aa56d170c3f594cda1ab3ffb6e7a2fcd3ef16d2cb099be38675162479e2547","abstract_canon_sha256":"c137d879f5c15ac8173e301a3eacc446325a60d8bbf38f7bd261a720a3e11299"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:46.794090Z","signature_b64":"Y9XubDcHIu+b5VhFu0gxVUyC1S1ssXhBun73ykvZiKI6EnAXmqIMD3+SndHkz0sDBk+5QtfyCWYUkHu3uNimBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f612e69b3309ed681449b0dd3949b90789a93807db724489aa032a9cab23c92","last_reissued_at":"2026-07-05T10:39:46.793529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:46.793529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MCBLT: Multi-Camera Multi-Object 3D Tracking in Long Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjamin Missaoui, Cheng-Yen Yang, Laura Leal-Taix\\'e, Orcun Cetintas, Sameer Satish Pusegaonkar, Sujit Biswas, Tim Meinhardt, Yizhou Wang, Zheng Tang","submitted_at":"2024-12-01T06:18:06Z","abstract_excerpt":"Object perception from multi-view cameras is crucial for intelligent systems, particularly in indoor environments, e.g., warehouses, retail stores, and hospitals. Most traditional multi-target multi-camera (MTMC) detection and tracking methods rely on 2D object detection, single-view multi-object tracking (MOT), and cross-view re-identification (ReID) techniques, without properly handling important 3D information by multi-view image aggregation. In this paper, we propose a 3D object detection and tracking framework, named MCBLT, which first aggregates multi-view images with necessary camera ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00692","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/2412.00692/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":"2412.00692","created_at":"2026-07-05T10:39:46.793609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00692v3","created_at":"2026-07-05T10:39:46.793609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00692","created_at":"2026-07-05T10:39:46.793609+00:00"},{"alias_kind":"pith_short_12","alias_value":"D5QS42NTGCPN","created_at":"2026-07-05T10:39:46.793609+00:00"},{"alias_kind":"pith_short_16","alias_value":"D5QS42NTGCPNNAKE","created_at":"2026-07-05T10:39:46.793609+00:00"},{"alias_kind":"pith_short_8","alias_value":"D5QS42NT","created_at":"2026-07-05T10:39:46.793609+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.09946","citing_title":"Online 3D Multi-Camera Perception through Robust 2D Tracking and Depth-based Late Aggregation","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D5QS42NTGCPNNAKETMG5HFE3SB","json":"https://pith.science/pith/D5QS42NTGCPNNAKETMG5HFE3SB.json","graph_json":"https://pith.science/api/pith-number/D5QS42NTGCPNNAKETMG5HFE3SB/graph.json","events_json":"https://pith.science/api/pith-number/D5QS42NTGCPNNAKETMG5HFE3SB/events.json","paper":"https://pith.science/paper/D5QS42NT"},"agent_actions":{"view_html":"https://pith.science/pith/D5QS42NTGCPNNAKETMG5HFE3SB","download_json":"https://pith.science/pith/D5QS42NTGCPNNAKETMG5HFE3SB.json","view_paper":"https://pith.science/paper/D5QS42NT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00692&json=true","fetch_graph":"https://pith.science/api/pith-number/D5QS42NTGCPNNAKETMG5HFE3SB/graph.json","fetch_events":"https://pith.science/api/pith-number/D5QS42NTGCPNNAKETMG5HFE3SB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D5QS42NTGCPNNAKETMG5HFE3SB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D5QS42NTGCPNNAKETMG5HFE3SB/action/storage_attestation","attest_author":"https://pith.science/pith/D5QS42NTGCPNNAKETMG5HFE3SB/action/author_attestation","sign_citation":"https://pith.science/pith/D5QS42NTGCPNNAKETMG5HFE3SB/action/citation_signature","submit_replication":"https://pith.science/pith/D5QS42NTGCPNNAKETMG5HFE3SB/action/replication_record"}},"created_at":"2026-07-05T10:39:46.793609+00:00","updated_at":"2026-07-05T10:39:46.793609+00:00"}