{"id":"W3015476328","doi":"10.1109/icassp40776.2020.9053919","title":"Facial Emotion Recognition Using Light Field Images with Deep Attention-Based Bidirectional LSTM","year":2020,"lang":"en","type":"article","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Light field; Deep learning; Viewpoints; Computer vision; Context (archaeology); Focus (optics); Facial recognition system; Field (mathematics); Pattern recognition (psychology); Feature extraction; Feature (linguistics)","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":[0.0001886247,0.0001019902,0.0001086385,0.00006343934,0.0001451055,0.0001346986,0.00015399,0.00004909283,0.00009639405],"category_scores_gemma":[0.00007249606,0.00008541103,0.00005767349,0.0003919394,0.00001325026,0.0004024891,0.00002749987,0.00009922475,0.00004552455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001868929,"about_ca_system_score_gemma":0.00005296054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003943317,"about_ca_topic_score_gemma":0.00001855052,"domain_scores_codex":[0.9990732,0.0001079884,0.0001422119,0.0003104453,0.0002164285,0.0001496986],"domain_scores_gemma":[0.9995093,0.000104261,0.00006497536,0.0001277973,0.0001237252,0.00006998154],"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":[0.0001593375,0.0001899842,0.05218527,0.0000908402,0.00009094259,0.00006008893,0.000469354,0.004344083,0.03354442,0.0005271937,0.001277936,0.9070606],"study_design_scores_gemma":[0.001683737,0.0007465049,0.04692231,0.0001010566,0.00003668512,0.00004748075,0.00007233866,0.7903472,0.1554913,0.00188055,0.001864469,0.0008063688],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04519825,0.00001356189,0.9478502,0.004699173,0.0002363654,0.00008154466,0.000001591296,0.0002421396,0.001677234],"genre_scores_gemma":[0.6587618,0.000001996153,0.3392959,0.001697965,0.0001996201,0.000004326259,0.000008104821,0.000007166522,0.00002310161],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9062542,"threshold_uncertainty_score":0.3482961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04488617254995769,"score_gpt":0.2787972901296638,"score_spread":0.2339111175797061,"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."}}