{"id":"W2158684487","doi":"10.1186/1687-5281-2013-8","title":"Automatic landmark point detection and tracking for human facial expressions","year":2013,"lang":"en","type":"article","venue":"EURASIP Journal on Image and Video Processing","topic":"Face recognition and analysis","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Landmark; Artificial intelligence; Computer science; Pattern recognition (psychology); Computer vision; Particle filter; Facial expression; Face detection; Biometrics; Feature (linguistics); Kernel (algebra); Facial recognition system; Mathematics; Kalman filter","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002787086,0.000114471,0.0001512434,0.0001727523,0.0009001337,0.001543238,0.0001149508,0.00003678687,0.00003268844],"category_scores_gemma":[0.0001018304,0.00008669258,0.00005843091,0.000127497,0.00003241337,0.001588358,0.00003496566,0.0001802672,0.00000698559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001560413,"about_ca_system_score_gemma":0.00001900482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004196885,"about_ca_topic_score_gemma":0.000002600946,"domain_scores_codex":[0.999177,0.00005160386,0.0002442109,0.0001958769,0.0001423189,0.0001889309],"domain_scores_gemma":[0.999409,0.00006968552,0.0001677645,0.0000701859,0.0001427409,0.0001406314],"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":[0.000002335545,0.00002207864,0.0001038409,0.00004570637,0.000009038941,0.000004550061,0.0004942922,0.000001258123,0.07337578,0.00001598963,0.0000859456,0.9258392],"study_design_scores_gemma":[0.006579708,0.001317855,0.07020784,0.003549692,0.0002614732,0.002137423,0.003043579,0.7065285,0.1421609,0.05922283,0.003119229,0.001870892],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5020912,0.0001927805,0.4961731,0.001109818,0.00006367514,0.0001161225,7.386641e-7,0.0000667511,0.0001858738],"genre_scores_gemma":[0.9861445,0.00002983435,0.01330767,0.0003256308,0.0001136145,0.00001302034,5.343981e-7,0.000008394619,0.00005680117],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9239683,"threshold_uncertainty_score":0.9994932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02223238108401342,"score_gpt":0.2894727997340698,"score_spread":0.2672404186500563,"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."}}