{"id":"W1480583224","doi":"10.1007/s12193-015-0195-2","title":"EmoNets: Multimodal deep learning approaches for emotion recognition in video","year":2015,"lang":"en","type":"article","venue":"Journal on Multimodal User Interfaces","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":401,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; Université de Montréal; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Artificial intelligence; Autoencoder; Convolutional neural network; Deep learning; Modalities; Classifier (UML); Modality (human–computer interaction); Feature learning; Test set; Pattern recognition (psychology); Machine learning","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00124032,0.0002945208,0.0003458826,0.0005232117,0.0001585392,0.0001540385,0.0002001399,0.0003095397,0.0004360586],"category_scores_gemma":[0.0004803929,0.0002628363,0.0001712551,0.0001894272,0.0000570599,0.0004833301,0.00003178208,0.0009551286,0.0006804627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002450495,"about_ca_system_score_gemma":0.00003379848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007791253,"about_ca_topic_score_gemma":0.000102254,"domain_scores_codex":[0.9975485,0.000526175,0.0006938773,0.0004412303,0.0003151601,0.0004751188],"domain_scores_gemma":[0.9986763,0.00023074,0.0004084685,0.0001509804,0.0002698501,0.0002636413],"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":[0.004710196,0.002182845,0.01180522,0.0000610865,0.0002652361,0.00005960804,0.02168656,0.01744048,0.0009188207,0.0001897355,0.003636238,0.937044],"study_design_scores_gemma":[0.08838297,0.02051891,0.2194055,0.003014119,0.0005450143,0.002133787,0.149846,0.4208722,0.01839975,0.01898916,0.05282515,0.005067475],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9737192,0.0001984416,0.01711578,0.0007196647,0.002516997,0.0005988509,0.00001381758,0.0001040409,0.005013216],"genre_scores_gemma":[0.9929742,0.00003280936,0.004650097,0.0002552702,0.0005946803,0.00008734087,0.00007326986,0.00005820282,0.001274102],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9319765,"threshold_uncertainty_score":0.9999824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1388529883662771,"score_gpt":0.344573290491237,"score_spread":0.20572030212496,"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."}}