{"id":"W4399206244","doi":"10.1109/tgrs.2024.3407761","title":"PointNAT: Large-Scale Point Cloud Semantic Segmentation via Neighbor Aggregation With Transformer","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Point cloud; Computer science; Segmentation; k-nearest neighbors algorithm; Artificial intelligence; Transformer; Cloud computing; Block (permutation group theory); Data mining; Pattern recognition (psychology); Machine learning; Mathematics; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001628334,0.0001586794,0.0001328812,0.0002382593,0.0002708218,0.0001318032,0.00003675852,0.00006022961,0.00001151422],"category_scores_gemma":[5.966108e-7,0.0001276227,0.00007002098,0.0005315391,0.00005735208,0.0002929031,2.826312e-7,0.0002026759,0.00001862319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004892418,"about_ca_system_score_gemma":0.00001871373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000101826,"about_ca_topic_score_gemma":0.0002324997,"domain_scores_codex":[0.9990618,0.0000164791,0.0001752212,0.0002802618,0.0002151108,0.0002511909],"domain_scores_gemma":[0.9997377,0.00002865232,0.00001279228,0.0001138088,0.0000306007,0.00007642403],"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":[0.00001420409,0.00001399751,3.848719e-7,0.0001139327,0.0000498606,0.00002154534,0.002428091,0.09330605,0.0297424,0.000002230933,0.000008379608,0.8742989],"study_design_scores_gemma":[0.0001496083,0.00005399975,0.00000751448,0.0002772603,0.00009726689,0.00009142473,0.0004490247,0.9499495,0.04860974,0.0001044736,0.00003634593,0.000173816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1569186,0.0001234295,0.8418417,0.0002508184,0.0003753871,0.00008669114,0.00000665606,0.0002548405,0.0001418704],"genre_scores_gemma":[0.9824165,0.0002584464,0.01699643,0.00006200556,0.0000505342,2.311345e-7,0.000002903588,0.0000250061,0.0001879704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8741251,"threshold_uncertainty_score":0.5204301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006337239837422007,"score_gpt":0.2127906512244171,"score_spread":0.2064534113869951,"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."}}