{"id":"W2884081170","doi":"10.1109/itsc.2018.8569793","title":"Leveraging Pre-Trained 3D Object Detection Models for Fast Ground Truth Generation","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Minimum bounding box; Artificial intelligence; Annotation; Object detection; Object (grammar); Task (project management); Bounding overwatch; Ground truth; Segmentation; Point cloud; Scheme (mathematics); Orientation (vector space); Generalization; Computer vision; Machine learning; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001481151,0.002762358,0.001287768,0.001765516,0.0006638182,0.001640372,0.004026477,0.00227954,0.004906667],"category_scores_gemma":[0.004309832,0.001724579,0.001239322,0.001360011,0.0009159554,0.002352359,0.00238812,0.002614668,0.005821314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001667073,"about_ca_system_score_gemma":0.001636536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01285873,"about_ca_topic_score_gemma":0.03208623,"domain_scores_codex":[0.9987337,0.0001194554,0.00003887546,0.0006159674,0.0003876089,0.0001042742],"domain_scores_gemma":[0.9975742,0.000702565,0.0001743496,0.0008704278,0.0006049181,0.00007356337],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002681145,0.0003195242,0.004198579,0.0002746496,0.0001719642,0.0002160417,0.0001591704,0.2104539,0.05874022,0.002273008,0.02119661,0.7017283],"study_design_scores_gemma":[0.00001218521,0.00006350715,0.001152408,0.00002348711,0.00001772109,0.00008273443,0.00002924276,0.9656748,0.02639848,0.002270476,0.004251997,0.00002287904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0214903,0.0002333786,0.9463531,0.0001426343,0.0001085924,0.000176348,0.001166356,0.02841766,0.001911676],"genre_scores_gemma":[0.2383191,0.0003093086,0.7460629,0.0003048368,0.00005330823,0.0003285193,0.008319119,0.001642012,0.004660834],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01285873,"threshold_uncertainty_score":0.02556783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04700156863065653,"score_gpt":0.2829623081059814,"score_spread":0.2359607394753249,"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."}}