{"id":"W4396696562","doi":"10.1016/j.jvcir.2024.104163","title":"Convolution-transformer blend pyramid network for underwater image enhancement","year":2024,"lang":"en","type":"article","venue":"Journal of Visual Communication and Image Representation","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Encoder; Underwater; Transformer; Convolutional neural network; Artificial intelligence; Computer vision; Pattern recognition (psychology); 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":[0.0009985287,0.0001229484,0.000177423,0.0001596524,0.0001770796,0.0005681633,0.0004250024,0.00004491819,0.00002938412],"category_scores_gemma":[0.00004970005,0.000107128,0.0001055952,0.0002570746,0.0001125691,0.002460437,0.00008953564,0.0001931913,0.000008833462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000816946,"about_ca_system_score_gemma":0.00007253299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009954118,"about_ca_topic_score_gemma":0.000002431891,"domain_scores_codex":[0.9986488,0.0001568251,0.0005576715,0.0001820008,0.0002694683,0.000185187],"domain_scores_gemma":[0.9987251,0.0002597085,0.0002283584,0.0003263749,0.0004013342,0.00005910714],"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":[0.0001529727,0.0003838765,0.0001002503,0.0003329403,0.000282886,0.00001382087,0.00317514,0.00004809929,0.7219722,0.03637931,0.05004405,0.1871145],"study_design_scores_gemma":[0.001566521,0.001262572,0.0008147306,0.0007124853,0.0001277258,0.0001557963,0.0005037419,0.1860387,0.722764,0.04760394,0.0379415,0.0005082524],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003106693,0.002120816,0.9895387,0.003602257,0.0002399972,0.0003459463,0.000001610174,0.00007882409,0.0009652049],"genre_scores_gemma":[0.5900249,0.00349156,0.4056654,0.0002115954,0.0001551931,0.00004045854,0.00002254847,0.00001657002,0.000371805],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5869182,"threshold_uncertainty_score":0.5478812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02330316752039279,"score_gpt":0.3654522559250257,"score_spread":0.3421490884046329,"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."}}