{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000625623,0.001200016,0.001024634,0.0007009004,0.0003397193,0.0005375543,0.002147056,0.0009634239,0.004279893],"category_scores_gemma":[0.001728923,0.0005118755,0.0006638074,0.0006985209,0.00048284,0.0008374043,0.002430634,0.00103276,0.001526298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002771222,"about_ca_system_score_gemma":0.0007805013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004410375,"about_ca_topic_score_gemma":0.01173562,"domain_scores_codex":[0.9994978,0.00006723544,0.00001717129,0.000115225,0.0002459762,0.00005665653],"domain_scores_gemma":[0.9995645,0.0001307081,0.00003868742,0.00009825577,0.0001351723,0.00003270864],"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":[0.0005858786,0.0001677432,0.001280049,0.0001243565,0.0001629474,0.0001873061,0.0001441477,0.09067375,0.04806769,0.003091257,0.009578819,0.8459361],"study_design_scores_gemma":[0.00003198123,0.00009650811,0.0009041779,0.00001509593,0.00002870798,0.0002027699,0.0000330008,0.974883,0.01752755,0.002431152,0.003818834,0.00002716794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00997141,0.000182015,0.9861027,0.00006195331,0.00007771161,0.00003349769,0.00007345885,0.002912214,0.0005850371],"genre_scores_gemma":[0.2523713,0.0002533153,0.7359016,0.0003359205,0.00007331582,0.000110801,0.0007062212,0.001267553,0.008979935],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004410375,"threshold_uncertainty_score":0.01431763,"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."}}