{"id":"W4395447900","doi":"10.1109/tgrs.2024.3393845","title":"3DGTN: 3-D Dual-Attention GLocal Transformer Network for Point Cloud Classification and Segmentation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Segmentation; Cloud computing; Glocalization; Artificial intelligence; Point cloud; Dual (grammatical number); Computer vision; Remote sensing; Geology","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":[0.0003490527,0.0007631457,0.0005022125,0.0006792529,0.0003069329,0.0005725409,0.00188931,0.0007899043,0.003262495],"category_scores_gemma":[0.00106173,0.0003972286,0.0006336445,0.0007770839,0.0005170193,0.001268358,0.001376019,0.0009784312,0.00103849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001142451,"about_ca_system_score_gemma":0.0008942637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01417574,"about_ca_topic_score_gemma":0.01800778,"domain_scores_codex":[0.999826,0.0000242553,0.000006309705,0.00005758494,0.00005324868,0.0000325734],"domain_scores_gemma":[0.9997925,0.00005363448,0.00001985356,0.00004579457,0.00006798927,0.00002023622],"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":[0.0002214521,0.0001132741,0.00178776,0.00009585581,0.00008184264,0.0001458796,0.0001013711,0.3938334,0.02313002,0.01267122,0.01265217,0.5551658],"study_design_scores_gemma":[0.000004656703,0.00001501768,0.0001803111,0.000003048729,0.000006226362,0.00002188031,0.000007575571,0.9925708,0.003291177,0.002754107,0.001140475,0.000004674782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01882045,0.0001974516,0.9750134,0.0001594287,0.00004687856,0.00005916338,0.0003507663,0.003183194,0.002169244],"genre_scores_gemma":[0.5724028,0.000456588,0.4121988,0.0003969384,0.00006598527,0.0002439305,0.002958637,0.0004644975,0.01081168],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01417574,"threshold_uncertainty_score":0.02818644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01676028151295976,"score_gpt":0.2455901903792387,"score_spread":0.228829908866279,"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."}}