{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002244525,0.002514855,0.001313931,0.001094487,0.0003994506,0.0007989111,0.003490259,0.001585953,0.003119951],"category_scores_gemma":[0.007118978,0.0008584003,0.001834081,0.0008699484,0.0009513742,0.001412654,0.00320035,0.002307605,0.002668293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000642816,"about_ca_system_score_gemma":0.0006932955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003565845,"about_ca_topic_score_gemma":0.006483719,"domain_scores_codex":[0.9978713,0.0005841776,0.00007461638,0.0009149215,0.0004205203,0.0001344758],"domain_scores_gemma":[0.9975289,0.0007968544,0.00016231,0.001152487,0.0002461389,0.0001134103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005309511,0.0004916713,0.004765911,0.0002760508,0.0004878712,0.0002970222,0.0001734565,0.3557235,0.01860672,0.002423307,0.02618207,0.5900415],"study_design_scores_gemma":[0.00004530558,0.0002501712,0.001771724,0.00002659045,0.00003175069,0.0003255668,0.00003594903,0.9793177,0.008600621,0.003956542,0.005598452,0.0000396654],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01954271,0.0006089817,0.9573408,0.000145834,0.0002817492,0.0003140311,0.001333271,0.0190964,0.001336118],"genre_scores_gemma":[0.3805874,0.0005323119,0.5924655,0.001003344,0.0002540675,0.001132958,0.01583114,0.002102702,0.006090621],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003565845,"threshold_uncertainty_score":0.01187027,"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."}}