{"id":"W4319300623","doi":"10.1109/wacv56688.2023.00426","title":"Multivariate Probabilistic Monocular 3D Object Detection","year":2023,"lang":"en","type":"article","venue":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Monocular; Artificial intelligence; Robustness (evolution); Probabilistic logic; Computer science; Covariance; Probability distribution; Multivariate statistics; Covariance matrix; Joint probability distribution; Computer vision; Posterior probability; Object detection; Pattern recognition (psychology); Mathematics; Machine learning; Algorithm; Bayesian probability; Statistics","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003654974,0.0004240827,0.0004626195,0.0005650865,0.0003342539,0.0002164853,0.002003984,0.0001672557,0.00004106493],"category_scores_gemma":[0.0000271928,0.0004135489,0.0002095261,0.00248929,0.0001746071,0.0004878503,0.0005804259,0.0004002691,0.001578791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001035585,"about_ca_system_score_gemma":0.00009565136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002425415,"about_ca_topic_score_gemma":0.00001725971,"domain_scores_codex":[0.996618,0.00016053,0.0008289624,0.001271008,0.0005743264,0.0005471724],"domain_scores_gemma":[0.9962836,0.0004197216,0.0004293409,0.002149816,0.000499654,0.0002178809],"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":[0.00006232846,0.0005767343,0.00003199279,0.0001034565,0.00009544918,0.00001184823,0.0004717259,0.03012849,0.04282137,0.05492454,0.004521158,0.8662509],"study_design_scores_gemma":[0.0005460573,0.0003993969,0.001725259,0.0001324973,0.00002038215,0.00001460693,0.00001727575,0.9543217,0.00839608,0.02339408,0.01053734,0.0004952703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005284802,0.00001720743,0.9893625,0.001347166,0.0004668333,0.001654794,0.00002706988,0.0009483931,0.0008912201],"genre_scores_gemma":[0.9033892,0.00006050989,0.09370531,0.0002986723,0.0002913114,0.001425576,0.00004907545,0.00005267301,0.000727728],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9241933,"threshold_uncertainty_score":0.9998316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02941803805642603,"score_gpt":0.3058455239599843,"score_spread":0.2764274859035583,"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."}}