{"id":"W4200586929","doi":"10.1109/tcyb.2021.3131569","title":"Robust and Precise Facial Landmark Detection by Self-Calibrated Pose Attention Network","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Face recognition and analysis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Shenzhen Science and Technology Innovation Program; Natural Science Foundation of Hubei Province; Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Landmark; Computer science; Artificial intelligence; Robustness (evolution); Benchmark (surveying); Pose; Computer vision; Pattern recognition (psychology); Facial expression","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":[0.0001026885,0.0001485231,0.0001534411,0.00007508073,0.0002390751,0.0002232277,0.0001227067,0.0001214219,0.0000810997],"category_scores_gemma":[0.000003450275,0.000156656,0.0001003413,0.0006618507,0.00002628368,0.0002415826,0.000003632784,0.000202576,0.00005615586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003751235,"about_ca_system_score_gemma":0.00003057878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002299557,"about_ca_topic_score_gemma":0.0001979045,"domain_scores_codex":[0.9988384,0.0001324097,0.0002145107,0.0003777102,0.0002130543,0.0002239539],"domain_scores_gemma":[0.9994056,0.00006381424,0.00005695027,0.0002336925,0.0001117393,0.0001282691],"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":[0.00006247481,0.001243638,0.0003201237,0.00005757472,0.000493423,0.0000509558,0.0005704968,0.07796484,0.03150195,0.0001383796,0.002882623,0.8847135],"study_design_scores_gemma":[0.0015104,0.0002245205,0.0009614719,0.00006419199,0.0002627306,0.00008950759,0.00007815877,0.8884675,0.09857178,0.000533028,0.008588728,0.0006479868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04664596,0.0001050788,0.9516809,0.0003061944,0.0006073933,0.00009093185,0.00001961085,0.0002321048,0.0003118496],"genre_scores_gemma":[0.9867939,0.0005402828,0.01096748,0.0002051117,0.000072446,0.00001686072,0.00001284047,0.00001578023,0.001375308],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9407134,"threshold_uncertainty_score":0.6388245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01225609249949205,"score_gpt":0.2019292537947988,"score_spread":0.1896731612953067,"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."}}