{"id":"W4226154576","doi":"10.1109/tim.2022.3162615","title":"Attention-Guided Multitask Convolutional Neural Network for Power Line Parts Detection","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Changsha Science and Technology Project; National Key Research and Development Program of China; State Key Laboratory of Robotics; National Natural Science Foundation of China","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Robustness (evolution); Feature extraction; Electric power transmission; Pattern recognition (psychology); Aerial image; Object detection; Computer vision; Machine learning; Image (mathematics); Engineering","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":[0.0003333127,0.0001518937,0.0001156506,0.0001006754,0.001285546,0.00005762871,0.0001695911,0.00002817173,0.00003890242],"category_scores_gemma":[0.000003611352,0.0001701092,0.00008981008,0.0003393726,0.00003645528,0.0002975491,0.000005851758,0.0001696164,0.000004877601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002920552,"about_ca_system_score_gemma":0.00004305481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008125473,"about_ca_topic_score_gemma":0.00004149023,"domain_scores_codex":[0.998386,0.00009282573,0.0003228449,0.0004104069,0.000535418,0.0002525525],"domain_scores_gemma":[0.9993318,0.0000552787,0.0001312329,0.0002286236,0.000154962,0.00009807961],"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":[0.0001535476,0.0004317984,0.00006747166,0.00001746796,0.00009660591,9.98361e-7,0.0002260902,0.8089436,0.02317289,0.005694964,0.0009712892,0.1602232],"study_design_scores_gemma":[0.007546719,0.002257198,0.003781201,0.00003766415,0.0001368976,0.0001370617,0.0004004475,0.9163367,0.03722548,0.005601211,0.02552468,0.00101472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01970219,0.00004106554,0.9764216,0.001197131,0.001501331,0.0009151468,0.00002940919,0.000155461,0.00003669914],"genre_scores_gemma":[0.9845837,0.00001614444,0.01288523,0.0007633465,0.00005231907,0.001563888,0.0000129444,0.00001356613,0.0001088163],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9648815,"threshold_uncertainty_score":0.9887514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05328217204729416,"score_gpt":0.2788850487255949,"score_spread":0.2256028766783008,"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."}}