{"id":"W4220904698","doi":"10.1109/tpami.2022.3159725","title":"Recurrent 3D Hand Pose Estimation Using Cascaded Pose-Guided 3D Alignments","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Key Research and Development Program of China; Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Pose; Articulated body pose estimation; 3D pose estimation; Margin (machine learning); Feature extraction; Recurrent neural network; Representation (politics)","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":[0.0004330443,0.001817076,0.001510275,0.0009074057,0.0003062186,0.0007200996,0.001784984,0.0008600598,0.00332153],"category_scores_gemma":[0.001638492,0.001011777,0.001131534,0.0009318481,0.000392708,0.001262325,0.001273901,0.001160425,0.002138902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005217852,"about_ca_system_score_gemma":0.000810529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007299871,"about_ca_topic_score_gemma":0.01365298,"domain_scores_codex":[0.9993643,0.00005160885,0.00002778118,0.000258045,0.0002235268,0.00007474206],"domain_scores_gemma":[0.9994325,0.0001096086,0.0001021764,0.0001527154,0.0001585276,0.00004438601],"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":[0.0002986301,0.0001115703,0.002180326,0.0001097789,0.0001677995,0.0003019864,0.0001291537,0.2140551,0.06535687,0.001599468,0.004025695,0.7116636],"study_design_scores_gemma":[0.00000839363,0.00005797778,0.0009731195,0.000008731674,0.00002479663,0.0001345196,0.0000134654,0.9854232,0.01112266,0.001286429,0.0009320935,0.00001469861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0198199,0.0002768154,0.9748325,0.00004825171,0.00004371627,0.00004236132,0.0001550246,0.003780488,0.001000892],"genre_scores_gemma":[0.5378971,0.0004525085,0.4539651,0.0002168076,0.00008793997,0.0001365002,0.001505971,0.0004936743,0.005244417],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007299871,"threshold_uncertainty_score":0.01451474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04414582110202018,"score_gpt":0.3029478812723079,"score_spread":0.2588020601702877,"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."}}