{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DH442N7VXJU5RD6CLPA633J5NQ","short_pith_number":"pith:DH442N7V","schema_version":"1.0","canonical_sha256":"19f9cd37f5ba69d88fc25bc1eded3d6c2be1d31b6bde79341a9e7fe72bed5f23","source":{"kind":"arxiv","id":"2208.10056","version":3},"attestation_state":"computed","paper":{"title":"Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jeannette Bohg, JunYoung Gwak, Silvio Savarese","submitted_at":"2022-08-22T04:47:40Z","abstract_excerpt":"Recent research in multi-task learning reveals the benefit of solving related problems in a single neural network. 3D object detection and multi-object tracking (MOT) are two heavily intertwined problems predicting and associating an object instance location across time. However, most previous works in 3D MOT treat the detector as a preceding separated pipeline, disjointly taking the output of the detector as an input to the tracker. In this work, we present Minkowski Tracker, a sparse spatio-temporal R-CNN that jointly solves object detection and tracking. Inspired by region-based CNN (R-CNN)"},"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":"2208.10056","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-22T04:47:40Z","cross_cats_sorted":[],"title_canon_sha256":"901b2d14c84cf8234506dc79aabde207ca867373a02cb2e880a67eb00ac221d2","abstract_canon_sha256":"c18518e320b42fed7f817f2a59bb1d3ff867b01e81afcf0855529b45c80bfe00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:42.982032Z","signature_b64":"49fL1RAdtOrSBE3KwmjnVAc7UjHGrRjsZaf/iURRquWMFijlVjuFtFCVfMXOjFyuud+nb4qNpNkWK9lpqAqxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19f9cd37f5ba69d88fc25bc1eded3d6c2be1d31b6bde79341a9e7fe72bed5f23","last_reissued_at":"2026-07-05T04:51:42.981677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:42.981677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jeannette Bohg, JunYoung Gwak, Silvio Savarese","submitted_at":"2022-08-22T04:47:40Z","abstract_excerpt":"Recent research in multi-task learning reveals the benefit of solving related problems in a single neural network. 3D object detection and multi-object tracking (MOT) are two heavily intertwined problems predicting and associating an object instance location across time. However, most previous works in 3D MOT treat the detector as a preceding separated pipeline, disjointly taking the output of the detector as an input to the tracker. In this work, we present Minkowski Tracker, a sparse spatio-temporal R-CNN that jointly solves object detection and tracking. Inspired by region-based CNN (R-CNN)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10056","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/2208.10056/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":"2208.10056","created_at":"2026-07-05T04:51:42.981731+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.10056v3","created_at":"2026-07-05T04:51:42.981731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10056","created_at":"2026-07-05T04:51:42.981731+00:00"},{"alias_kind":"pith_short_12","alias_value":"DH442N7VXJU5","created_at":"2026-07-05T04:51:42.981731+00:00"},{"alias_kind":"pith_short_16","alias_value":"DH442N7VXJU5RD6C","created_at":"2026-07-05T04:51:42.981731+00:00"},{"alias_kind":"pith_short_8","alias_value":"DH442N7V","created_at":"2026-07-05T04:51:42.981731+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20892","citing_title":"To New Beginnings: A Survey of Unified Perception in Autonomous Vehicle Software","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DH442N7VXJU5RD6CLPA633J5NQ","json":"https://pith.science/pith/DH442N7VXJU5RD6CLPA633J5NQ.json","graph_json":"https://pith.science/api/pith-number/DH442N7VXJU5RD6CLPA633J5NQ/graph.json","events_json":"https://pith.science/api/pith-number/DH442N7VXJU5RD6CLPA633J5NQ/events.json","paper":"https://pith.science/paper/DH442N7V"},"agent_actions":{"view_html":"https://pith.science/pith/DH442N7VXJU5RD6CLPA633J5NQ","download_json":"https://pith.science/pith/DH442N7VXJU5RD6CLPA633J5NQ.json","view_paper":"https://pith.science/paper/DH442N7V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.10056&json=true","fetch_graph":"https://pith.science/api/pith-number/DH442N7VXJU5RD6CLPA633J5NQ/graph.json","fetch_events":"https://pith.science/api/pith-number/DH442N7VXJU5RD6CLPA633J5NQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DH442N7VXJU5RD6CLPA633J5NQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DH442N7VXJU5RD6CLPA633J5NQ/action/storage_attestation","attest_author":"https://pith.science/pith/DH442N7VXJU5RD6CLPA633J5NQ/action/author_attestation","sign_citation":"https://pith.science/pith/DH442N7VXJU5RD6CLPA633J5NQ/action/citation_signature","submit_replication":"https://pith.science/pith/DH442N7VXJU5RD6CLPA633J5NQ/action/replication_record"}},"created_at":"2026-07-05T04:51:42.981731+00:00","updated_at":"2026-07-05T04:51:42.981731+00:00"}