{"id":"W1968728049","doi":"10.1109/oceans.2014.7003118","title":"Automatic fish counting system for noisy deep-sea videos","year":2014,"lang":"en","type":"article","venue":"","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ocean Networks Canada Society; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Preprocessor; Artificial intelligence; Background subtraction; Computer vision; Noise (video); Fish <Actinopterygii>; Modular design; Tracking (education); Object detection; Pattern recognition (psychology); Image (mathematics); Pixel","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":[0.0006071397,0.0001094479,0.000141982,0.00002338105,0.000135492,0.00006121225,0.0003807278,0.00007910998,0.0001041163],"category_scores_gemma":[0.0003577685,0.00009055947,0.00004400314,0.00009529674,0.00008530318,0.0001550713,0.0002260015,0.00005690929,0.0004451193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002024874,"about_ca_system_score_gemma":0.000002030841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003187825,"about_ca_topic_score_gemma":0.00007132848,"domain_scores_codex":[0.9989869,0.0000317711,0.0002251641,0.0002452925,0.0002182377,0.0002926463],"domain_scores_gemma":[0.999337,0.0001710846,0.00007479128,0.0003691592,0.000009914525,0.0000380601],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002348312,0.0002348971,0.6279206,0.001916294,0.00009593833,0.000007340232,0.001378154,0.002206037,0.0351775,0.01394678,0.09605723,0.2210357],"study_design_scores_gemma":[0.001267026,0.0003065462,0.1123206,0.0002340386,0.0000697788,0.00001851601,0.001782265,0.5422897,0.2701475,0.005691993,0.06469942,0.001172612],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9563404,0.000002015732,0.03485358,0.0007085961,0.0004532943,0.000366551,0.00000304893,0.001761029,0.005511498],"genre_scores_gemma":[0.9666763,2.259983e-7,0.03268993,0.00009529787,0.00007487955,0.00007691782,0.000002047057,0.00001458214,0.0003698264],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5400836,"threshold_uncertainty_score":0.5721256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01900096113051058,"score_gpt":0.2392257721593601,"score_spread":0.2202248110288495,"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."}}