{"id":"W4316876965","doi":"10.1109/tai.2023.3237787","title":"Accelerating Point-Voxel Representation of 3-D Object Detection for Automatic Driving","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Voxel; Computer science; Artificial intelligence; Feature (linguistics); Representation (politics); Computer vision; Benchmark (surveying); Matching (statistics); Object (grammar); Point (geometry); Pattern recognition (psychology); Set (abstract data type); 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":[0.0002414817,0.0001418289,0.0001752969,0.0002959024,0.0004154555,0.00008158385,0.0004162576,0.00006194367,0.00001354774],"category_scores_gemma":[0.00005382218,0.0001550969,0.0001377954,0.001984466,0.00005911691,0.0005325235,0.000005252009,0.0001562126,0.00009884033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005661227,"about_ca_system_score_gemma":0.00003232802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001814751,"about_ca_topic_score_gemma":0.0001180882,"domain_scores_codex":[0.9984505,0.00005858225,0.0005384503,0.0004395629,0.0002346996,0.0002781913],"domain_scores_gemma":[0.998273,0.0008329569,0.0001879696,0.0004992385,0.0001456598,0.00006124523],"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":[0.000008085091,0.00005470145,0.000001373422,0.00001478964,0.00001040947,6.177027e-7,0.0003912319,0.2092973,0.08483514,0.003467581,0.00001228239,0.7019065],"study_design_scores_gemma":[0.00001503268,0.00006278631,0.00002025385,0.00001816754,0.000005853339,0.00000217494,0.00009904931,0.5169252,0.4689807,0.01378516,0.000008472826,0.0000771442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03127342,0.000003316943,0.9665286,0.0003262945,0.0006224755,0.0006100647,0.00000554552,0.0005773482,0.00005292325],"genre_scores_gemma":[0.9547861,0.00001740992,0.04467589,0.0000411412,0.00005458217,0.0003421166,0.00000185245,0.00001801185,0.00006292894],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9235126,"threshold_uncertainty_score":0.6324669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09089608000098295,"score_gpt":0.3478067514297102,"score_spread":0.2569106714287273,"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."}}