{"id":"W4377001482","doi":"10.1109/joe.2023.3252759","title":"U-MSAA-Net: A Multiscale Additive Attention-Based Network for Pixel-Level Identification of Finfish and Krill in Echograms","year":2023,"lang":"en","type":"article","venue":"IEEE Journal of Oceanic Engineering","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Fisheries and Oceans Canada; ASL Environmental Sciences (Canada); University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Krill; Fishery; Computer science; Artificial intelligence; Environmental science; Pattern recognition (psychology); Biology","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":[0.0007036843,0.00009250458,0.0001754609,0.0001220509,0.0000279094,0.00001752275,0.0001814072,0.00006868286,0.000004015781],"category_scores_gemma":[0.0002054866,0.00009149584,0.0000644523,0.0003448934,0.00004607784,0.0001604519,0.00003848455,0.0001382215,0.000003393867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009598211,"about_ca_system_score_gemma":0.000006382624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001332893,"about_ca_topic_score_gemma":0.000006832748,"domain_scores_codex":[0.9990214,0.0000159197,0.0004604805,0.0001171768,0.0001861058,0.0001989506],"domain_scores_gemma":[0.9993876,0.0002099152,0.0002258814,0.0001189347,0.00002157014,0.00003610026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00005299278,0.00009032312,0.09903634,0.0001591132,0.00006114049,0.00001628699,0.0004401749,0.6534008,0.2327896,0.00003739317,0.00271408,0.01120175],"study_design_scores_gemma":[0.001069011,0.0001786011,0.787181,0.0003944722,0.00003097618,0.00001225471,0.0001797715,0.1542342,0.05499157,0.000511248,0.0009787445,0.0002381542],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9629719,0.00003036813,0.03625974,0.000117302,0.0004093368,0.0001384968,0.00002292082,0.00004715284,0.000002722135],"genre_scores_gemma":[0.9893904,0.00003236965,0.01043022,0.000003923978,0.00008703757,0.000007168517,0.000003225888,0.00001463804,0.00003105994],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6881447,"threshold_uncertainty_score":0.3731092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02682217917744567,"score_gpt":0.2538022623644307,"score_spread":0.226980083186985,"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."}}