{"id":"W3155665398","doi":"10.1109/taffc.2021.3072579","title":"MDN: A Deep Maximization-Differentiation Network for Spatio-Temporal Depression Detection","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Affective Computing","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":127,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Overfitting; Maximization; Facial expression; Discriminative model; Computer science; Code (set theory); Artificial intelligence; Deep learning; Pattern recognition (psychology); Machine learning; Mathematics; Mathematical optimization; Artificial neural network","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":[0.0002380437,0.000216198,0.0002219908,0.0001613389,0.0006680964,0.00006286184,0.00006392713,0.0002092448,0.0004660241],"category_scores_gemma":[0.00002631036,0.0002389625,0.0002205524,0.0004469896,0.00002730192,0.0001224007,0.000002019998,0.000280107,0.00007728134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000132031,"about_ca_system_score_gemma":0.00002973378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000307388,"about_ca_topic_score_gemma":0.0006190527,"domain_scores_codex":[0.9982764,0.0003880969,0.0003172649,0.0005400285,0.0001452802,0.000332923],"domain_scores_gemma":[0.9987355,0.000430425,0.000191459,0.0002209366,0.0003347978,0.00008680846],"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":[0.0004903358,0.0008214092,0.001374426,0.00006747056,0.0002973897,0.000006647679,0.001402527,0.1126145,0.00244553,0.0002084695,0.0003360519,0.8799352],"study_design_scores_gemma":[0.01077491,0.001196008,0.07487576,0.0005998622,0.0006487374,0.0002182102,0.001733543,0.7193373,0.1839009,0.00352746,0.001657478,0.001529898],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1321315,0.00006160231,0.8617721,0.00005367936,0.004199887,0.0006215258,0.00001642902,0.0002447593,0.0008985584],"genre_scores_gemma":[0.9942557,0.000006879792,0.004495558,0.0001667702,0.000433295,0.000134173,0.0001332523,0.00004774333,0.0003266107],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8784053,"threshold_uncertainty_score":0.9744607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02320631289779015,"score_gpt":0.291019335747294,"score_spread":0.2678130228495039,"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."}}