{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3CUBTUO5BHSFZIKLJEAEVHJW2U","short_pith_number":"pith:3CUBTUO5","schema_version":"1.0","canonical_sha256":"d8a819d1dd09e45ca14b49004a9d36d502352063afaf246114f81db23a176476","source":{"kind":"arxiv","id":"2003.11753","version":1},"attestation_state":"computed","paper":{"title":"Real-time 3D Deep Multi-Camera Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Jiang, Quanzeng You","submitted_at":"2020-03-26T06:08:19Z","abstract_excerpt":"Tracking a crowd in 3D using multiple RGB cameras is a challenging task. Most previous multi-camera tracking algorithms are designed for offline setting and have high computational complexity. Robust real-time multi-camera 3D tracking is still an unsolved problem. In this work, we propose a novel end-to-end tracking pipeline, Deep Multi-Camera Tracking (DMCT), which achieves reliable real-time multi-camera people tracking. Our DMCT consists of 1) a fast and novel perspective-aware Deep GroudPoint Network, 2) a fusion procedure for ground-plane occupancy heatmap estimation, 3) a novel Deep Glim"},"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":"2003.11753","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-26T06:08:19Z","cross_cats_sorted":[],"title_canon_sha256":"691d351e42ea362f4b42dd4bbd86c0b3039b0adbd48d3cbbd14076ed50d9e57f","abstract_canon_sha256":"f27a57703154d7b555b485e18639bad42a0dcbb90aaeceef9427b6583459c2bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:50:47.071650Z","signature_b64":"HjisnWrWcSKmZC3d4mb/2V6tNY/dhGMBy8aGT1PzVDmAXCQnRrm/uSX+ClZ8df5MKILa6k/FXTkwXsyDCQMBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8a819d1dd09e45ca14b49004a9d36d502352063afaf246114f81db23a176476","last_reissued_at":"2026-07-05T00:50:47.071186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:50:47.071186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real-time 3D Deep Multi-Camera Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Jiang, Quanzeng You","submitted_at":"2020-03-26T06:08:19Z","abstract_excerpt":"Tracking a crowd in 3D using multiple RGB cameras is a challenging task. Most previous multi-camera tracking algorithms are designed for offline setting and have high computational complexity. Robust real-time multi-camera 3D tracking is still an unsolved problem. In this work, we propose a novel end-to-end tracking pipeline, Deep Multi-Camera Tracking (DMCT), which achieves reliable real-time multi-camera people tracking. Our DMCT consists of 1) a fast and novel perspective-aware Deep GroudPoint Network, 2) a fusion procedure for ground-plane occupancy heatmap estimation, 3) a novel Deep Glim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.11753","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/2003.11753/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":"2003.11753","created_at":"2026-07-05T00:50:47.071243+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.11753v1","created_at":"2026-07-05T00:50:47.071243+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.11753","created_at":"2026-07-05T00:50:47.071243+00:00"},{"alias_kind":"pith_short_12","alias_value":"3CUBTUO5BHSF","created_at":"2026-07-05T00:50:47.071243+00:00"},{"alias_kind":"pith_short_16","alias_value":"3CUBTUO5BHSFZIKL","created_at":"2026-07-05T00:50:47.071243+00:00"},{"alias_kind":"pith_short_8","alias_value":"3CUBTUO5","created_at":"2026-07-05T00:50:47.071243+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00273","citing_title":"MVDGC: Joint 3D and 2D Multi-view Pedestrian Detection via Dual Geometric Constraints","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09245","citing_title":"CalibFree: Self-Supervised View Feature Separation for Calibration-Free Multi-Camera Multi-Object Tracking","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19318","citing_title":"Multi-view Crowd Tracking Transformer with View-Ground Interactions Under Large Real-World Scenes","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3CUBTUO5BHSFZIKLJEAEVHJW2U","json":"https://pith.science/pith/3CUBTUO5BHSFZIKLJEAEVHJW2U.json","graph_json":"https://pith.science/api/pith-number/3CUBTUO5BHSFZIKLJEAEVHJW2U/graph.json","events_json":"https://pith.science/api/pith-number/3CUBTUO5BHSFZIKLJEAEVHJW2U/events.json","paper":"https://pith.science/paper/3CUBTUO5"},"agent_actions":{"view_html":"https://pith.science/pith/3CUBTUO5BHSFZIKLJEAEVHJW2U","download_json":"https://pith.science/pith/3CUBTUO5BHSFZIKLJEAEVHJW2U.json","view_paper":"https://pith.science/paper/3CUBTUO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.11753&json=true","fetch_graph":"https://pith.science/api/pith-number/3CUBTUO5BHSFZIKLJEAEVHJW2U/graph.json","fetch_events":"https://pith.science/api/pith-number/3CUBTUO5BHSFZIKLJEAEVHJW2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3CUBTUO5BHSFZIKLJEAEVHJW2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3CUBTUO5BHSFZIKLJEAEVHJW2U/action/storage_attestation","attest_author":"https://pith.science/pith/3CUBTUO5BHSFZIKLJEAEVHJW2U/action/author_attestation","sign_citation":"https://pith.science/pith/3CUBTUO5BHSFZIKLJEAEVHJW2U/action/citation_signature","submit_replication":"https://pith.science/pith/3CUBTUO5BHSFZIKLJEAEVHJW2U/action/replication_record"}},"created_at":"2026-07-05T00:50:47.071243+00:00","updated_at":"2026-07-05T00:50:47.071243+00:00"}