{"id":"W3034664537","doi":"10.1109/cvpr42600.2020.01297","title":"Adaptive Hierarchical Down-Sampling for Point Cloud Classification","year":2020,"lang":"en","type":"article","venue":"","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":154,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Point cloud; Computer science; Sampling (signal processing); Cloud computing; Adaptive sampling; Artificial intelligence; Algorithm; Data mining; Computer vision; Mathematics; Monte Carlo method; Statistics","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":[0.0005500008,0.0009363902,0.001053854,0.001024938,0.000488443,0.000683192,0.002302532,0.000811642,0.00262641],"category_scores_gemma":[0.001857538,0.0005550095,0.001104229,0.001130476,0.0006717377,0.001543054,0.001423721,0.001618032,0.001060112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001232162,"about_ca_system_score_gemma":0.001182284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01385743,"about_ca_topic_score_gemma":0.01894678,"domain_scores_codex":[0.9995083,0.00005189852,0.00002439315,0.000135144,0.0001953395,0.0000849792],"domain_scores_gemma":[0.9993876,0.0001527714,0.00006377769,0.0001867434,0.0001656705,0.00004342389],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000399796,0.0001651022,0.003960807,0.0001453678,0.00009946302,0.0001752647,0.0001023297,0.5129644,0.02744621,0.009154988,0.006428356,0.4389579],"study_design_scores_gemma":[0.000005366546,0.00001868691,0.0003283187,0.000003369514,0.000004263607,0.00001984308,0.000006081233,0.994418,0.003004574,0.001692833,0.0004941787,0.000004472156],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04244362,0.0002877938,0.9530051,0.0001395505,0.00004961099,0.00008945858,0.0003840489,0.002577391,0.001023402],"genre_scores_gemma":[0.5617065,0.0003784726,0.430279,0.0002556047,0.00006589648,0.0002310288,0.002963878,0.0003409842,0.003778673],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01385743,"threshold_uncertainty_score":0.02755356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0783438641277904,"score_gpt":0.260565337854999,"score_spread":0.1822214737272086,"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."}}