{"id":"W4313007980","doi":"10.1109/cvpr52688.2022.01273","title":"AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Pose; Artificial intelligence; Estimator; Motion capture; 3D pose estimation; Generalization; Computer vision; Machine learning; Orientation (vector space); Pattern recognition (psychology); Motion (physics); Mathematics","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":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000697552,0.0003730875,0.0003277889,0.0003857327,0.001654437,0.001091663,0.0004025289,0.0001310731,0.001088838],"category_scores_gemma":[0.00001561274,0.0004079641,0.0001103422,0.000295237,0.00005580807,0.001514286,0.0001865834,0.0004163566,0.0001562485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001312086,"about_ca_system_score_gemma":0.00005858762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006732942,"about_ca_topic_score_gemma":0.00003004619,"domain_scores_codex":[0.9968472,0.0004184733,0.0006488537,0.001029192,0.0006626789,0.0003936715],"domain_scores_gemma":[0.9985282,0.0001131657,0.0004286111,0.0004220376,0.0003283113,0.0001797016],"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":[0.00005652629,0.0003830336,0.00002723779,0.00005046412,0.00002830548,0.000007969624,0.0003700252,0.002103086,0.007575078,0.0003694369,0.05147457,0.9375542],"study_design_scores_gemma":[0.001809559,0.00179968,0.0002517929,0.00005774451,0.0000258156,0.00004701872,0.00005238873,0.9826696,0.002957904,0.002348824,0.007435197,0.0005444536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0875335,0.00002651499,0.9072632,0.0008258534,0.001510057,0.0008513646,0.001605893,0.0002260609,0.0001575388],"genre_scores_gemma":[0.9570056,0.00006558865,0.01370462,0.003312211,0.0005324951,0.0005239879,0.02438206,0.00004607097,0.0004273609],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9805666,"threshold_uncertainty_score":0.9999453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08461681226342394,"score_gpt":0.3228882606346563,"score_spread":0.2382714483712324,"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."}}