{"id":"W3099113948","doi":"10.1109/wacv48630.2021.00307","title":"Temporal Stochastic Softmax for 3D CNNs: An Application in Facial Expression Recognition","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Compute Canada","keywords":"Softmax function; Computer science; Artificial intelligence; Convolutional neural network; Pooling; Inference; Weighting; Pattern recognition (psychology); Sampling (signal processing); Speech recognition; Deep learning; Machine learning; Computer vision","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":[0.0003972541,0.0003070142,0.0003517671,0.0002774789,0.0001280352,0.0003942687,0.0006705143,0.0004955515,0.00005274783],"category_scores_gemma":[0.00009140222,0.0003013629,0.0001291012,0.0002065326,0.00002377629,0.0008681623,0.0006634647,0.0004159156,0.00004653636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009150521,"about_ca_system_score_gemma":0.0002158099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002299407,"about_ca_topic_score_gemma":0.000262801,"domain_scores_codex":[0.9975099,0.0001315909,0.0005277258,0.001167063,0.0003335153,0.0003301829],"domain_scores_gemma":[0.9984876,0.00009867636,0.0002688545,0.0007449034,0.0002693096,0.0001306664],"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":[0.0001002338,0.0006951471,0.0001291964,0.0003383755,0.00001525626,0.000007379521,0.00180757,0.003781558,0.01958999,0.0001297295,0.001141883,0.9722637],"study_design_scores_gemma":[0.001732974,0.0002129695,0.0005267485,0.001360092,0.00002743127,0.00001009137,0.0006383326,0.9261327,0.02392713,0.04315151,0.0009587552,0.00132125],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05502936,0.00005415929,0.9421555,0.0002131299,0.0006864701,0.001306698,0.00004766642,0.0002741428,0.0002328542],"genre_scores_gemma":[0.5277238,0.00002210552,0.4659643,0.000346491,0.0003043121,0.002340153,0.003157388,0.00003311024,0.0001083752],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9709424,"threshold_uncertainty_score":0.9999439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04416350885950689,"score_gpt":0.2943202847817362,"score_spread":0.2501567759222293,"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."}}