{"id":"W2953941229","doi":"10.1109/cvpr.2019.01214","title":"Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction","year":2019,"lang":"en","type":"article","venue":"","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":328,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Computer vision; Artificial intelligence; Monocular; Benchmark (surveying); Point cloud; Minimum bounding box; Object (grammar); Object detection; Bounding overwatch; Projection (relational algebra); Key (lock); Set (abstract data type); Exploit; Convolutional neural network; Pinhole (optics); Pattern recognition (psychology); Image (mathematics); Algorithm","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":[0.001090836,0.001807089,0.001636061,0.001411696,0.0005095128,0.001324885,0.003012217,0.001590585,0.003440243],"category_scores_gemma":[0.00299609,0.000896214,0.001051221,0.001356455,0.0008220471,0.001800489,0.003273306,0.00105532,0.003440578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007163252,"about_ca_system_score_gemma":0.001699564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005438393,"about_ca_topic_score_gemma":0.01086021,"domain_scores_codex":[0.9987323,0.0001425634,0.00003412593,0.0004323924,0.0005259613,0.0001326053],"domain_scores_gemma":[0.9989126,0.0002138768,0.0001265128,0.0004105828,0.0002400575,0.00009646786],"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":[0.0003040588,0.0001525363,0.002376105,0.0002785463,0.0001696815,0.0003043932,0.0001479048,0.1270069,0.04789104,0.005474304,0.01094601,0.8049485],"study_design_scores_gemma":[0.00001981587,0.00009872387,0.0008182034,0.0000213779,0.00001589433,0.000324611,0.0000309214,0.9792824,0.01278344,0.003167721,0.003411642,0.00002524359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0174479,0.0004245576,0.9733132,0.0001153099,0.000066234,0.00007451228,0.0002480287,0.006340083,0.001970081],"genre_scores_gemma":[0.210414,0.0003587043,0.7819614,0.0002667494,0.00007009001,0.0001171212,0.001573298,0.0006849982,0.004553482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005438393,"threshold_uncertainty_score":0.0115087,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008285531654501792,"score_gpt":0.1890609395199843,"score_spread":0.1807754078654825,"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."}}