{"id":"W2742792558","doi":"10.1145/3063592","title":"Mobile Multi-Food Recognition Using Deep Learning","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":85,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Minimum bounding box; Set (abstract data type); Deep learning; Cloud computing; Process (computing); Pattern recognition (psychology); Submodular set function; Machine learning; Computer vision; Image (mathematics); Mathematics","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0001707777,0.0001793795,0.0002428093,0.000120108,0.00451838,0.0001106534,0.0004946597,0.00009990578,0.00002616045],"category_scores_gemma":[0.00007984461,0.0001873883,0.0001143973,0.0001323111,0.0003922731,0.0001146548,0.0001024927,0.0004947573,0.00004422266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006380586,"about_ca_system_score_gemma":0.00003116784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009359053,"about_ca_topic_score_gemma":0.00005169473,"domain_scores_codex":[0.9989479,0.00005400358,0.0003135313,0.000321661,0.0001441498,0.0002187791],"domain_scores_gemma":[0.9972028,0.0003596829,0.0002041828,0.001838426,0.000237554,0.0001573816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003018386,0.001273631,0.002994397,0.00005657772,0.0001703919,7.109182e-7,0.0003953521,0.0003341526,0.001219157,0.00009293065,0.00001047001,0.993422],"study_design_scores_gemma":[0.01005282,0.001722441,0.0655821,0.0008611482,0.001194143,0.0002437616,0.004139112,0.8117275,0.001508877,0.002061184,0.09947152,0.00143536],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09524105,0.002406246,0.8959858,0.002085738,0.0001237749,0.002382005,0.0001309109,0.0003844321,0.001259984],"genre_scores_gemma":[0.7163386,0.002337205,0.2806847,0.00009170194,0.00007566384,0.0003084192,0.00009023232,0.00002328992,0.0000501664],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9919867,"threshold_uncertainty_score":0.9967776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08922163145647409,"score_gpt":0.3552259678272213,"score_spread":0.2660043363707472,"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."}}