{"id":"W4318832773","doi":"10.3390/s23031555","title":"PA-Tran: Learning to Estimate 3D Hand Pose with Partial Annotation","year":2023,"lang":"en","type":"article","venue":"Sensors","topic":"Hand Gesture Recognition Systems","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Annotation; Artificial intelligence; Computer science; Convolutional neural network; Pattern recognition (psychology); Pose; Encoder; Encoding (memory); Partial least squares regression; RGB color model; Automatic image annotation; Embedding; Deep learning; Set (abstract data type); Image (mathematics); Machine learning; Image retrieval; Computer vision","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":[0.0007742757,0.002412886,0.001498786,0.0007329897,0.0002923794,0.0009713475,0.001949963,0.00139416,0.004468363],"category_scores_gemma":[0.002984193,0.001115911,0.001106379,0.0007203577,0.0006640868,0.002019041,0.001828647,0.001796124,0.003030743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003789829,"about_ca_system_score_gemma":0.000908723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004978442,"about_ca_topic_score_gemma":0.008522727,"domain_scores_codex":[0.9992687,0.00008675538,0.00002995896,0.0003562626,0.0001705021,0.00008786596],"domain_scores_gemma":[0.9990973,0.0003135614,0.00009239521,0.0002669959,0.0001728651,0.0000569346],"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":[0.0003988104,0.0001709463,0.002604102,0.000202736,0.0001834953,0.0001635898,0.00009241759,0.1332376,0.02836,0.001604989,0.008985076,0.8239963],"study_design_scores_gemma":[0.00001701449,0.0001280608,0.001153463,0.00002649787,0.0000262117,0.0002253309,0.00002273089,0.9850338,0.008625296,0.002069774,0.002648883,0.00002295146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01867723,0.0005927061,0.9689709,0.00008621262,0.00009226692,0.00009782016,0.0004907325,0.009531653,0.0014605],"genre_scores_gemma":[0.3924077,0.0008744865,0.5873599,0.0005033148,0.0002197599,0.0003589128,0.005654203,0.000870134,0.01175156],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004978442,"threshold_uncertainty_score":0.01494813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01699116160898646,"score_gpt":0.2804752527647815,"score_spread":0.2634840911557951,"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."}}