{"id":"W2980080875","doi":"10.1109/tits.2019.2939536","title":"Corse-to-Fine Road Extraction Based on Local Dirichlet Mixture Models and Multiscale-High-Order Deep Learning","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Huaqiao University; Xiamen University; Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Dirichlet distribution; Feature extraction; Pattern recognition (psychology); Deep learning; Shape context; False positive paradox; Image (mathematics); Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015532,0.0003943612,0.0003650216,0.0004699231,0.0001776683,0.00008241331,0.00009920762,0.0003111018,0.0001413752],"category_scores_gemma":[0.000001983906,0.0003930914,0.0001147663,0.0004882313,0.0000277437,0.0003534926,1.885554e-7,0.0006342489,0.0002494831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001891979,"about_ca_system_score_gemma":0.00001608253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002660236,"about_ca_topic_score_gemma":0.0001957381,"domain_scores_codex":[0.9980499,0.00007034075,0.0005977085,0.0004836163,0.0004596107,0.0003388698],"domain_scores_gemma":[0.9992071,0.0001281704,0.00009525956,0.000253706,0.0001297999,0.0001859601],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001237312,0.0001221369,0.00004874568,0.00018999,0.00006644978,0.000006902851,0.0004861654,0.960569,0.008021169,0.00006681133,0.00003073463,0.03026816],"study_design_scores_gemma":[0.0005662435,0.0002640443,0.001137445,0.0003160038,0.00007578571,0.000008664461,0.0004904849,0.9770754,0.01832061,0.000007163972,0.001301972,0.0004362005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2135209,0.00008433445,0.78259,0.0000336529,0.002141538,0.0006675053,0.00004784584,0.0007278409,0.0001864439],"genre_scores_gemma":[0.9983351,0.00009484556,0.0006611816,0.00004204207,0.00006530005,0.0001508748,0.00008497864,0.0001027254,0.0004630056],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7848142,"threshold_uncertainty_score":0.9998521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009947630863455195,"score_gpt":0.2285120932382165,"score_spread":0.2185644623747613,"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."}}