{"id":"W4200096726","doi":"10.1109/iai53119.2021.9619442","title":"Development of New Efficient Transposed Convolution Techniques for Flame Segmentation from UAV-captured Images","year":2021,"lang":"en","type":"article","venue":"","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Upsampling; Computer science; Convolution (computer science); Artificial intelligence; Feature (linguistics); Bilinear interpolation; Segmentation; Bicubic interpolation; Computer vision; Kernel (algebra); Deep learning; Interpolation (computer graphics); Convolutional neural network; Encoder; Pattern recognition (psychology); Image (mathematics); Linear interpolation; Artificial neural network; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002008941,0.0001424674,0.0001830747,0.00008336764,0.0000677092,0.00005922214,0.0003409569,0.00006382626,0.00005180524],"category_scores_gemma":[0.00002111936,0.0001388436,0.00006967549,0.0002300807,0.00002434016,0.0002446394,0.00007381487,0.00004925544,0.000004833223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009797222,"about_ca_system_score_gemma":0.0002905614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003386349,"about_ca_topic_score_gemma":0.00002697528,"domain_scores_codex":[0.9987156,0.00003196198,0.0004015416,0.0003801129,0.0002760447,0.0001947136],"domain_scores_gemma":[0.999219,0.00005305734,0.0001259178,0.0003286125,0.0002237184,0.00004970282],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001065052,0.00008082791,0.0000115162,0.00001730984,0.00001961594,0.000001449744,0.001387618,0.000005744852,0.9225451,0.001433871,0.001506173,0.07298011],"study_design_scores_gemma":[0.0003765577,0.00003880241,0.0003641553,0.00004857558,0.00001019471,8.001475e-7,0.00008688003,0.003778707,0.9921554,0.0009457932,0.002030488,0.0001636021],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009295219,0.0001235545,0.9885874,0.0003516718,0.0001214432,0.0005605425,0.000006848556,0.0004434678,0.0005098656],"genre_scores_gemma":[0.1504156,0.000008906054,0.848729,0.000137633,0.00002801776,0.00007650385,0.00006805958,0.000008814032,0.000527517],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1411204,"threshold_uncertainty_score":0.5661879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01899137984741532,"score_gpt":0.2677675899054451,"score_spread":0.2487762100580297,"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."}}