{"id":"W2890072312","doi":"10.3390/rs10091496","title":"Detecting Building Edges from High Spatial Resolution Remote Sensing Imagery Using Richer Convolution Features Network","year":2018,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote Sensing and Land Use","field":"Earth and Planetary Sciences","cited_by":69,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Toronto; National Natural Science Foundation of China","keywords":"Computer science; Constraint (computer-aided design); Enhanced Data Rates for GSM Evolution; Measure (data warehouse); Convolution (computer science); Edge detection; Artificial intelligence; Feature (linguistics); Building model; Aerial image; Remote sensing; Pattern recognition (psychology); Image (mathematics); Computer vision; Data mining; Image processing; Mathematics; Geology; Geometry; Simulation; Artificial neural network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0009068601,0.0004670856,0.000522716,0.0002121526,0.001513576,0.0003668592,0.0001449097,0.0003766869,0.00005436089],"category_scores_gemma":[0.0004310144,0.0004393014,0.0001722734,0.0006204912,0.0002770733,0.0003151715,0.0000523659,0.0006189649,0.00008510464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008317391,"about_ca_system_score_gemma":0.0001080644,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1387902,"about_ca_topic_score_gemma":0.01358043,"domain_scores_codex":[0.9963632,0.0005504275,0.0005768331,0.0008697064,0.0005329059,0.001106896],"domain_scores_gemma":[0.998137,0.0004947307,0.0003130651,0.0005495971,0.0002605709,0.0002450306],"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":[0.0001849471,0.000001964307,0.0004346526,0.00001383314,0.00005830648,0.0001082028,0.0003143357,0.01671502,0.02139287,7.174019e-7,0.0002124273,0.9605627],"study_design_scores_gemma":[0.0004220568,0.00007585101,0.02231042,0.0005909535,0.0001185757,0.0003309629,0.0001317149,0.964565,0.008322701,0.001845037,0.0007055796,0.000581148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7075897,0.0006289187,0.2874063,0.0001253794,0.002791923,0.0001532867,0.000008846956,0.0002549069,0.001040713],"genre_scores_gemma":[0.7192689,0.00004023647,0.2744271,0.0002541689,0.005873684,1.674735e-10,0.00005638094,0.00002961649,0.00004991185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9599816,"threshold_uncertainty_score":0.9998059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02057838936552527,"score_gpt":0.2341030529680952,"score_spread":0.2135246636025699,"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."}}