{"id":"W4312304153","doi":"10.1109/jiot.2022.3231369","title":"F-PVNet: Frustum-Level 3-D Object Detection on Point–Voxel Feature Representation for Autonomous Driving","year":2022,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Science and Technology Program of Suzhou; China Postdoctoral Science Foundation; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Computer science; Point cloud; Artificial intelligence; Robustness (evolution); Frustum; Object detection; Feature (linguistics); Feature extraction; Voxel; Pattern recognition (psychology); Computer vision; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000473512,0.0001598521,0.0001999042,0.0002295335,0.0004065144,0.0001471352,0.001065017,0.0000494666,0.00002114766],"category_scores_gemma":[0.0001013416,0.0001600753,0.000193378,0.0003464751,0.00002924751,0.0007751895,0.0002129492,0.0007425544,0.000005101433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003039845,"about_ca_system_score_gemma":0.00005275727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002055067,"about_ca_topic_score_gemma":0.000006466283,"domain_scores_codex":[0.998417,0.000104428,0.0003989127,0.0003767669,0.0004293959,0.0002735136],"domain_scores_gemma":[0.9984649,0.000273419,0.0006561072,0.0003678644,0.0001482981,0.0000893691],"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":[0.0005690899,0.0005952231,0.000623857,0.00005138838,0.0003104717,0.00008147006,0.01330407,0.145057,0.2177502,0.01250282,0.06557338,0.543581],"study_design_scores_gemma":[0.001661178,0.001837614,0.002011514,0.000127071,0.0000466976,0.002296808,0.0003702703,0.5966259,0.3361993,0.04286294,0.01534105,0.0006195621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06136423,0.00003981185,0.9343656,0.001797851,0.001704614,0.0003210665,0.000004243641,0.00009857998,0.0003040275],"genre_scores_gemma":[0.946423,0.000007992025,0.05119248,0.0006075382,0.0002752028,0.00008379637,0.000002553022,0.00002299321,0.001384439],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8850588,"threshold_uncertainty_score":0.652768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02940677403342595,"score_gpt":0.2912204584592035,"score_spread":0.2618136844257775,"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."}}