{"id":"W3192435669","doi":"10.1109/acii52823.2021.9597460","title":"Spatiotemporal Contrastive Learning of Facial Expressions in Videos","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Mitacs","keywords":"Computer science; Sampling (signal processing); Artificial intelligence; Scheme (mathematics); Pattern recognition (psychology); Facial expression; Sampling scheme; Deep learning; Speech recognition; Computer vision; Mathematics; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002059582,0.000162834,0.0003546833,0.0001540411,0.00005094281,0.0001677723,0.0005902797,0.000178262,0.00006305991],"category_scores_gemma":[0.0002329327,0.0001527076,0.00009091829,0.0002166276,0.00003738113,0.000258249,0.001283932,0.0006567851,0.000003255543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003701195,"about_ca_system_score_gemma":0.0004702549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000297748,"about_ca_topic_score_gemma":0.00008042634,"domain_scores_codex":[0.9985772,0.0001057459,0.0003630717,0.0004783201,0.0002625433,0.0002131297],"domain_scores_gemma":[0.9991723,0.00009203,0.000252795,0.000286132,0.0001361262,0.00006060442],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000505617,0.0006825098,0.1180917,0.0008181944,0.0001490828,0.000472079,0.02390765,0.04433092,0.108529,0.002083801,0.000493999,0.7003905],"study_design_scores_gemma":[0.0009345849,0.0000767136,0.03654864,0.002305405,0.00001203177,0.000008309825,0.001206729,0.06118736,0.8928151,0.003768645,0.0003619755,0.0007745535],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1969287,0.0002320461,0.797794,0.0002706952,0.0003307756,0.0001322816,0.000001983114,0.00008805798,0.004221461],"genre_scores_gemma":[0.9039683,0.00001696256,0.09567255,0.0000538157,0.0000442196,0.00001303609,0.00001045108,0.00000628816,0.0002143756],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.784286,"threshold_uncertainty_score":0.6227236,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01938747326674388,"score_gpt":0.2701144699575886,"score_spread":0.2507269966908448,"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."}}