{"id":"W4281696822","doi":"10.1016/j.jag.2022.102836","title":"SD-GCN: Saliency-based dilated graph convolution network for pavement crack extraction from 3D point clouds","year":2022,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Xiamen University; National Natural Science Foundation of China","keywords":"Point cloud; Leverage (statistics); Dilation (metric space); Convolution (computer science); Feature extraction; Computer science; Graph; Artificial intelligence; Pattern recognition (psychology); Computer vision; Mathematics; Artificial neural network; Geometry; Theoretical computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002667977,0.0007266036,0.0005277371,0.0008214571,0.0002682697,0.0003592196,0.0009852936,0.0005332177,0.001347343],"category_scores_gemma":[0.000938547,0.0002961124,0.0005907881,0.0006639134,0.0003651283,0.0008521728,0.0006482422,0.0004882747,0.0003454486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008129424,"about_ca_system_score_gemma":0.000691026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01572707,"about_ca_topic_score_gemma":0.01862269,"domain_scores_codex":[0.9998411,0.00001361411,0.000007500165,0.00005570725,0.00005296995,0.00002912149],"domain_scores_gemma":[0.99978,0.00005547847,0.00002619016,0.00002944119,0.00009205187,0.00001682403],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002675857,0.00009984777,0.003157561,0.0001514698,0.00009463337,0.0002782138,0.0001050875,0.5315889,0.03629224,0.003776002,0.005159687,0.4190288],"study_design_scores_gemma":[0.000003465161,0.00002068988,0.0005332329,0.000003334559,0.00000906218,0.00004291259,0.000006058722,0.9945957,0.003178786,0.001056165,0.0005455157,0.000005034424],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06686109,0.0004379969,0.9269606,0.0001744433,0.000077261,0.00007538607,0.0003998798,0.002845461,0.002167786],"genre_scores_gemma":[0.7491167,0.0004036185,0.2437093,0.0001953543,0.00005845999,0.000113065,0.00139082,0.0001591674,0.004853479],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01572707,"threshold_uncertainty_score":0.03127104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008712121307573921,"score_gpt":0.2126980240529828,"score_spread":0.2039859027454089,"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."}}