{"id":"W2973821056","doi":"10.1109/icra40945.2020.9196660","title":"Object-Centric Stereo Matching for 3D Object Detection","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer vision; Point cloud; Artificial intelligence; Computer science; Object (grammar); Lidar; Object detection; Stereo cameras; Matching (statistics); Computer stereo vision; Stereopsis; Focus (optics); Point (geometry); Pattern recognition (psychology); Geography; Mathematics; Remote sensing","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"],"consensus_categories":[],"category_scores_codex":[0.0001948374,0.0002935505,0.0003258511,0.0001955625,0.0001772916,0.0004672937,0.001000922,0.0001227888,0.00002207978],"category_scores_gemma":[0.00008765982,0.0002720766,0.0002064821,0.0002941236,0.00001384754,0.0004049497,0.001767752,0.000512638,0.00007447565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001213463,"about_ca_system_score_gemma":0.000118004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003713366,"about_ca_topic_score_gemma":0.000009739935,"domain_scores_codex":[0.9980052,0.00005452473,0.0003552145,0.0009419275,0.0002797114,0.0003634788],"domain_scores_gemma":[0.9987347,0.0001343894,0.0002089354,0.0006822202,0.0001014904,0.0001382583],"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":[0.00001636568,0.00003162045,0.00001480168,0.0002032641,0.00003102097,0.000008896616,0.0007533251,0.0009096966,0.002353379,0.001666326,0.0005163083,0.993495],"study_design_scores_gemma":[0.0005116745,0.00007891723,0.0001461825,0.0001140907,0.00001693099,0.00001638302,0.0000769089,0.9363264,0.009276396,0.04107292,0.0117971,0.0005661064],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002666785,0.0001573388,0.9925424,0.0007685791,0.002054497,0.0006353785,0.000004849609,0.0007427903,0.002827414],"genre_scores_gemma":[0.22585,0.00004678832,0.7716571,0.001522212,0.000289874,0.00007424108,0.000008684749,0.00003218622,0.0005189328],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9929289,"threshold_uncertainty_score":0.9999731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02918119997022833,"score_gpt":0.2982711453506043,"score_spread":0.269089945380376,"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."}}