{"id":"W2791299004","doi":"10.1049/iet-cvi.2016.0335","title":"Mid‐level deep Food Part mining for food image recognition","year":2018,"lang":"en","type":"article","venue":"IET Computer Vision","topic":"Advanced Chemical Sensor Technologies","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Qatar National Research Fund","keywords":"Computer science; Benchmark (surveying); Artificial intelligence; Convolutional neural network; Deep learning; Pattern recognition (psychology); Image (mathematics); Machine learning; Cluster analysis; Contextual image classification; Range (aeronautics)","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":[0.00003385554,0.0001663648,0.0001575649,0.00006411593,0.00006773802,0.00003942481,0.0001731148,0.0001397341,0.0000164366],"category_scores_gemma":[0.00003803843,0.0001665383,0.00006500274,0.0001226731,0.00006141723,0.000185976,0.00007796537,0.0001033895,0.00005817935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004741673,"about_ca_system_score_gemma":0.000001214559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":1.016178e-7,"about_ca_topic_score_gemma":0.000004518598,"domain_scores_codex":[0.9991429,0.000005909269,0.0002046555,0.0002498451,0.000100835,0.0002958215],"domain_scores_gemma":[0.9994922,0.0001051068,0.0000353112,0.0002291016,0.00009208018,0.000046183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003815029,0.0000467428,0.00001231696,0.0001191276,0.00006163771,0.000002801615,0.0001665029,0.0005274881,0.2424775,0.00003243173,0.01521937,0.741296],"study_design_scores_gemma":[0.0006367913,0.001257168,0.00007590878,0.0001272391,0.00001288329,0.00001049189,0.00002384139,0.06747603,0.904678,0.007826066,0.01753118,0.0003444135],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4389565,0.00005674763,0.5589772,0.00006148169,0.0005349978,0.0001624043,0.00004613142,0.0009975554,0.0002069991],"genre_scores_gemma":[0.699224,0.00001199612,0.3001113,0.00005173708,0.0004994869,0.00002057685,0.00003492872,0.00003953998,0.000006453021],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7409515,"threshold_uncertainty_score":0.6791234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03517998909312763,"score_gpt":0.2514308873356337,"score_spread":0.2162508982425061,"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."}}