{"id":"W4318768848","doi":"10.1109/access.2023.3241835","title":"Contactless Drink Intake Monitoring Using Depth Data","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"RGB color model; Convolutional neural network; Computer science; Artificial intelligence; Computer vision; Task (project management); Deep learning; Assisted living; Medicine; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001116268,0.0005690001,0.0004077624,0.0004786973,0.0001211316,0.000377619,0.0003667047,0.0003885595,0.002466514],"category_scores_gemma":[0.0007975195,0.0001949739,0.0002982737,0.0004389008,0.0001169557,0.0005389769,0.0005621599,0.0002479784,0.0007196094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002146479,"about_ca_system_score_gemma":0.0002490575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003348561,"about_ca_topic_score_gemma":0.009056882,"domain_scores_codex":[0.9998054,0.00002947217,0.000009588362,0.00005796646,0.00007253213,0.00002505814],"domain_scores_gemma":[0.9997768,0.00003586254,0.00004832524,0.00002347585,0.00009842089,0.0000171326],"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":[0.001943845,0.0005479783,0.1496355,0.00167242,0.0003455951,0.0007034296,0.000560669,0.01705959,0.2753205,0.0009208471,0.01303118,0.5382584],"study_design_scores_gemma":[0.00008518531,0.0009680833,0.4225148,0.0003035057,0.0002588162,0.00204193,0.0010901,0.3613663,0.1815899,0.00244315,0.02719715,0.0001411573],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7745188,0.002224771,0.1958047,0.0003864781,0.0001903185,0.0002967703,0.009950784,0.002527879,0.01409938],"genre_scores_gemma":[0.9481667,0.0007571589,0.04431621,0.0001723887,0.00004439358,0.0001213992,0.002857113,0.00008369057,0.00348099],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003348561,"threshold_uncertainty_score":0.00825125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3379492623789843,"score_gpt":0.4214592378918497,"score_spread":0.08350997551286549,"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."}}