{"id":"W2997890711","doi":"10.1109/tgrs.2019.2958517","title":"TGNet: Geometric Graph CNN on 3-D Point Cloud Segmentation","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":138,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Point cloud; Computer science; Segmentation; Artificial intelligence; Pattern recognition (psychology); Convolution (computer science); Parametric statistics; Gaussian; Conditional random field; Mathematics; Artificial neural network","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002493947,0.001651816,0.0008846726,0.001256036,0.000369726,0.0008598386,0.002210469,0.001018418,0.00324054],"category_scores_gemma":[0.0006996692,0.0006306322,0.001176531,0.001521076,0.0006537368,0.001731306,0.001370414,0.001001782,0.001637981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001484004,"about_ca_system_score_gemma":0.001329735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02307337,"about_ca_topic_score_gemma":0.0304259,"domain_scores_codex":[0.9997184,0.00001847608,0.00001060176,0.0001183963,0.00007641385,0.00005779219],"domain_scores_gemma":[0.9998516,0.00001913567,0.00002076488,0.00004411204,0.00004535865,0.00001898951],"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":[0.0002444467,0.0001398433,0.002664512,0.0001749022,0.0002251652,0.0003051216,0.0001252065,0.4610246,0.02228473,0.01066833,0.02340256,0.4787406],"study_design_scores_gemma":[0.000008260982,0.00003156678,0.0004739619,0.000008932967,0.00001624525,0.00006627951,0.00001550193,0.9878343,0.00490893,0.00449035,0.00213502,0.00001058072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05846496,0.0008192511,0.9113997,0.0004092864,0.0002377944,0.0001407902,0.001799346,0.02169187,0.005036981],"genre_scores_gemma":[0.5917157,0.0008340852,0.3852664,0.0006708652,0.0001080243,0.0002290605,0.01009682,0.001013331,0.01006581],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02307337,"threshold_uncertainty_score":0.04587817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009653795698255524,"score_gpt":0.2123240746829362,"score_spread":0.2026702789846807,"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."}}