{"id":"W2939498466","doi":"10.1109/tcsvt.2020.2984241","title":"Learned 3D Shape Representations Using Fused Geometrically Augmented Images: Application to Facial Expression and Action Unit Detection","year":2020,"lang":"en","type":"preprint","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Face recognition and analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Discriminative model; Pattern recognition (psychology); Feature (linguistics); Representation (politics); Convolutional neural network; Facial expression; Expression (computer science); Image (mathematics); Property (philosophy); Computer vision","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002552017,0.000329842,0.0005247616,0.002016353,0.0006045866,0.0003416955,0.0003668434,0.000536063,0.00000549456],"category_scores_gemma":[0.00006600738,0.0003491561,0.0001413582,0.001657529,0.00007497446,0.0002668198,0.00003362368,0.0005853129,0.00001240948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001420788,"about_ca_system_score_gemma":0.00007661272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002502485,"about_ca_topic_score_gemma":0.00004971332,"domain_scores_codex":[0.9974965,0.0001217094,0.0005901957,0.001195602,0.0002938388,0.0003020962],"domain_scores_gemma":[0.9984414,0.0001303286,0.0003442362,0.0005680943,0.0003253369,0.0001906279],"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":[0.00003191361,0.0001108982,0.00001641949,0.0003022657,0.0001518039,0.000002641374,0.0001888574,0.01616527,0.3564581,0.00009724144,0.00001958399,0.626455],"study_design_scores_gemma":[0.001043373,0.0003317687,0.00008460378,0.0002573118,0.0002347933,0.00005909497,0.0005739431,0.9076369,0.08679209,0.001066474,0.001329471,0.0005901582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03658563,0.0001340958,0.9593778,0.0009504973,0.0005821389,0.001619961,0.0001245214,0.0006078161,0.00001753057],"genre_scores_gemma":[0.9950544,0.000203752,0.003563322,0.00008633629,0.00005827093,0.0009241325,0.0000182488,0.00003206898,0.00005949786],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9584687,"threshold_uncertainty_score":0.999896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08211408856296784,"score_gpt":0.3243767265492116,"score_spread":0.2422626379862437,"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."}}