{"id":"W2800846474","doi":"10.1109/tgrs.2018.2802935","title":"Semantic Labeling of Mobile LiDAR Point Clouds via Active Learning and Higher Order MRF","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":71,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Point cloud; Consistency (knowledge bases); Artificial intelligence; Conditional random field; Set (abstract data type); Markov random field; Lidar; Point (geometry); Machine learning; Annotation; Supervised learning; Range (aeronautics); Data mining; Image (mathematics); Image segmentation; Remote sensing","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000241613,0.0001551542,0.0001740808,0.00008004452,0.0007344729,0.00004161728,0.000065548,0.00008304074,0.00006447386],"category_scores_gemma":[0.00000785489,0.0001374246,0.00003712616,0.000548848,0.0009948319,0.000154702,0.000007975359,0.0002378924,0.00004243184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004191696,"about_ca_system_score_gemma":0.00001676233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001587828,"about_ca_topic_score_gemma":0.0001635319,"domain_scores_codex":[0.9987716,0.00006029061,0.0002100888,0.0004386558,0.0002421459,0.0002772283],"domain_scores_gemma":[0.9994763,0.00008274515,0.00009569856,0.0001891237,0.00004386841,0.0001123104],"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":[0.00001591867,0.00002312376,0.000007265865,0.000006601712,0.000007444031,0.000001736393,0.001228542,0.0003869095,0.1888104,0.000001404879,0.000004744269,0.8095059],"study_design_scores_gemma":[0.001010251,0.001116396,0.003884686,0.0003575399,0.0001716942,0.0003595462,0.002590963,0.5067717,0.4734781,0.001102592,0.008196184,0.0009602947],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5927106,0.0000145873,0.4050037,0.0001887581,0.000190106,0.0001425331,0.000001473244,0.00004613809,0.001702146],"genre_scores_gemma":[0.9484929,0.00007613908,0.05039153,0.0001094963,0.00003633679,9.704467e-8,3.791486e-7,0.00001494283,0.0008782202],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8085456,"threshold_uncertainty_score":0.5649046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007787756091510549,"score_gpt":0.2399672333189703,"score_spread":0.2321794772274598,"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."}}