{"id":"W3133598367","doi":"10.1109/cvpr46437.2021.00845","title":"Categorical Depth Distribution Network for Monocular 3D Object Detection","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Monocular; Artificial intelligence; Computer vision; Computer science; Object detection; Benchmark (surveying); Bounding overwatch; Object (grammar); Monocular vision; Projection (relational algebra); Categorical variable; Pixel; Feature (linguistics); Minimum bounding box; Pattern recognition (psychology); Image (mathematics); Algorithm; Geography; Machine learning","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":[0.001232372,0.0002757041,0.0004144465,0.0000403313,0.000202439,0.000516657,0.0006591686,0.0003835643,0.000005199098],"category_scores_gemma":[0.0001977957,0.0002616555,0.0003279327,0.0003665487,0.0000199696,0.0001801485,0.0007300491,0.0004615168,0.000006320668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001757513,"about_ca_system_score_gemma":0.0002028256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002323789,"about_ca_topic_score_gemma":0.0003795398,"domain_scores_codex":[0.9977034,0.0003158392,0.0003591357,0.0009101943,0.000257432,0.0004540485],"domain_scores_gemma":[0.9982418,0.0002808583,0.0001711866,0.0009501133,0.0002606755,0.00009540591],"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":[0.00002335086,0.00009353875,0.001846487,0.0001909822,0.0001878536,0.00003887247,0.0001233271,0.03745442,0.0001533197,0.006733297,0.001203324,0.9519512],"study_design_scores_gemma":[0.000470611,0.0001376298,0.02370268,0.00007073541,0.00006449681,0.00005200781,0.0000149017,0.9087353,0.007904188,0.04587524,0.01203298,0.0009392717],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001844215,0.0006204245,0.9928802,0.000189833,0.003293432,0.000428987,0.000007243334,0.0003917202,0.000343954],"genre_scores_gemma":[0.5837923,0.00007386936,0.414931,0.0000977509,0.000620451,0.0001645875,0.0002337253,0.00001596399,0.00007029314],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.951012,"threshold_uncertainty_score":0.9999835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03501080092167862,"score_gpt":0.3029737313526659,"score_spread":0.2679629304309873,"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."}}