{"id":"W4402738247","doi":"10.1016/j.neucom.2024.128605","title":"ESCAPE: Energy-based Selective Adaptive Correction for Out-of-distribution 3D Human Pose Estimation","year":2024,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Artificial intelligence; Pose; Distribution (mathematics); Energy (signal processing); Estimation; Pattern recognition (psychology); 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":[0.000199255,0.0001416363,0.0001385987,0.0001662609,0.0002858319,0.0001651804,0.0001586985,0.00006695375,0.000004437203],"category_scores_gemma":[0.00004157351,0.0001523859,0.0001086119,0.0003924065,0.00002140107,0.0003977139,0.00003945997,0.000141617,0.00001178577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009524361,"about_ca_system_score_gemma":0.00009006252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001717801,"about_ca_topic_score_gemma":0.000006860431,"domain_scores_codex":[0.998836,0.00007928461,0.0002854879,0.0004166084,0.000180858,0.000201767],"domain_scores_gemma":[0.9991937,0.0002751962,0.0001420238,0.0001379573,0.0002078482,0.00004321789],"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":[0.00003744548,0.0001852741,0.00002144245,0.0001397429,0.0000486036,0.00001028489,0.0007035885,0.02920512,0.01731141,0.03046748,0.007330393,0.9145392],"study_design_scores_gemma":[0.0002231196,0.0003131437,0.0002060058,0.0001295605,0.00001888458,0.000006372399,0.000009264289,0.951597,0.0432158,0.002508174,0.001635709,0.0001369254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009318985,0.00002283394,0.9870383,0.00008596216,0.002274087,0.0002301389,0.00001085265,0.0004790098,0.0005398226],"genre_scores_gemma":[0.9854128,6.826515e-7,0.01398455,0.00010888,0.0002756859,0.00003256042,0.0001054363,0.00001503021,0.0000643122],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9760939,"threshold_uncertainty_score":0.6214116,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02334270311971516,"score_gpt":0.2792721938619526,"score_spread":0.2559294907422375,"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."}}