{"id":"W4291007208","doi":"10.1016/j.jag.2022.102953","title":"LEARD-Net: Semantic segmentation for large-scale point cloud scene","year":2022,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China","keywords":"Point cloud; Focus (optics); Segmentation; Computer science; Feature (linguistics); Scale (ratio); Benchmark (surveying); Artificial intelligence; Cloud computing; Feature extraction; Data mining; Pattern recognition (psychology); Geography; Cartography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006482367,0.002367105,0.001266742,0.003346215,0.001142334,0.001412392,0.00285675,0.001506093,0.005365023],"category_scores_gemma":[0.001786445,0.0008398347,0.001602032,0.002829159,0.000660002,0.002759253,0.002834603,0.001286737,0.002840567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001740084,"about_ca_system_score_gemma":0.001581623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01986072,"about_ca_topic_score_gemma":0.03088716,"domain_scores_codex":[0.9994891,0.00003847626,0.00003029397,0.0002217359,0.0001524196,0.00006799769],"domain_scores_gemma":[0.9995795,0.00007864516,0.00004749335,0.0001277949,0.000117628,0.00004897441],"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":[0.0008926768,0.0005303041,0.008710866,0.0007567334,0.0004847723,0.0004114892,0.0004144252,0.1968962,0.02060383,0.01214336,0.07724395,0.6809114],"study_design_scores_gemma":[0.00005594328,0.0001095753,0.002069307,0.00004572276,0.00008438093,0.0001532911,0.0001557603,0.9506007,0.01364137,0.01211328,0.02092605,0.00004462621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05237333,0.001281183,0.870567,0.0006144753,0.0002660451,0.000748446,0.01645442,0.05026314,0.007431905],"genre_scores_gemma":[0.2483409,0.0007798333,0.677449,0.0004908709,0.0001103325,0.0008313885,0.06208785,0.001532217,0.008377501],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01986072,"threshold_uncertainty_score":0.03949022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01119330001143662,"score_gpt":0.2199203393301543,"score_spread":0.2087270393187177,"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."}}