{"id":"W4401357138","doi":"10.1109/tits.2024.3436015","title":"Crack-U<sup>2</sup>Net: Multiscale Feature Learning Network for Pavement Crack Detection From Large-Scale MLS Point Clouds","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Scale (ratio); Feature (linguistics); Point cloud; Computer science; Point (geometry); Net (polyhedron); Artificial intelligence; Geography; Mathematics; Cartography","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":[0.0002991279,0.0004535455,0.000409202,0.0002058247,0.0003621659,0.0002054515,0.0001490973,0.0003434166,0.0001022982],"category_scores_gemma":[0.000002287882,0.0004492376,0.0003743079,0.0003906936,0.00002694859,0.0003082486,4.039126e-7,0.0007542667,0.00008835562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000309338,"about_ca_system_score_gemma":0.00002769452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001626708,"about_ca_topic_score_gemma":0.0004034691,"domain_scores_codex":[0.9976614,0.00005826882,0.0007335826,0.0005548979,0.0003738133,0.0006180683],"domain_scores_gemma":[0.9991701,0.0001942833,0.00007039514,0.0002747221,0.0001377066,0.0001527787],"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":[0.00007078318,0.00003478655,0.00007869397,0.0003989954,0.0002930225,0.00001063431,0.00526919,0.9779329,0.003350946,0.00004673128,0.0005910582,0.01192221],"study_design_scores_gemma":[0.0005653319,0.0001949607,0.0002395952,0.00100561,0.0002714962,0.000007727714,0.004384692,0.8443895,0.07747014,0.0001162515,0.0707169,0.0006378014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08599062,0.0009170804,0.9024329,0.00003498546,0.008042994,0.001019123,0.0005248035,0.0009788451,0.00005860946],"genre_scores_gemma":[0.9946054,0.0003012535,0.001878717,0.00002613962,0.00128164,0.0006384982,0.0002274907,0.0001545425,0.0008863149],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9086148,"threshold_uncertainty_score":0.9997959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009040371970213531,"score_gpt":0.2266541846195849,"score_spread":0.2176138126493714,"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."}}