{"id":"W4408712481","doi":"10.1109/itsc58415.2024.10919741","title":"3D Object Detection with Track-Based Auto-Labelling Using Very Sparsely Labelled Data","year":2024,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Labelling; Object (grammar); Object detection; Artificial intelligence; Track (disk drive); Computer vision; Track-before-detect; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001936235,0.0001861086,0.0001714601,0.0001628602,0.0001179475,0.00005230261,0.0002385041,0.0001923578,0.00009464353],"category_scores_gemma":[0.000008838391,0.0001615247,0.00002625057,0.0004071015,0.00005241337,0.00028511,0.00004111893,0.0003888249,0.00008481213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001025622,"about_ca_system_score_gemma":0.0000735763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000420141,"about_ca_topic_score_gemma":0.00014794,"domain_scores_codex":[0.9990643,0.00001703057,0.0001961642,0.0003356219,0.0001062762,0.0002805691],"domain_scores_gemma":[0.9993262,0.00007733538,0.00001507406,0.000527024,0.00001558988,0.00003878436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001135042,0.00007917257,0.0005078746,0.0005734894,0.0005566704,0.0003128376,0.0002308126,0.6518134,0.1857567,0.0005550677,0.0002933806,0.1592071],"study_design_scores_gemma":[0.0002392564,0.00004038611,0.00009364016,0.00007874196,0.00006766164,0.0000297696,0.00002158199,0.9525408,0.04373899,0.00004297886,0.002886032,0.0002201707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3787825,0.001023109,0.6131037,0.00004172775,0.0003585617,0.0001685909,0.0000188931,0.004751105,0.001751692],"genre_scores_gemma":[0.9839174,0.00002625075,0.01576626,0.00002871372,0.00005800026,0.000005828775,0.00002200658,0.00005855604,0.0001170202],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6051348,"threshold_uncertainty_score":0.6586785,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04337745361477451,"score_gpt":0.2346527600208068,"score_spread":0.1912753064060323,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}