{"id":"W4385431685","doi":"10.1016/j.jvcir.2023.103908","title":"Iterative graph filtering network for 3D human pose estimation","year":2023,"lang":"en","type":"article","venue":"Journal of Visual Communication and Image Representation","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Adjacency matrix; Pose; Computer science; Graph; Artificial intelligence; Adjacency list; Normalization (sociology); Algorithm; Pattern recognition (psychology); Laplacian matrix; Theoretical computer science","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006550245,0.00007436579,0.0001304491,0.0002289979,0.0003729731,0.0003072586,0.0002174199,0.00003284901,0.00000993354],"category_scores_gemma":[0.0001076405,0.00007166568,0.0000678436,0.0003715958,0.00003675115,0.001659137,0.00008739869,0.0001162863,0.000007153785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001986757,"about_ca_system_score_gemma":0.00001656937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005178162,"about_ca_topic_score_gemma":0.000002406727,"domain_scores_codex":[0.999048,0.0001802984,0.0003936065,0.0001088576,0.0001625028,0.0001067577],"domain_scores_gemma":[0.998719,0.000251144,0.0004305957,0.0001981833,0.000351967,0.00004912354],"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":[0.0002023045,0.0005058402,0.001115506,0.0002018149,0.0002853044,0.00001776634,0.01249238,0.005486708,0.1537212,0.02503257,0.04150774,0.7594309],"study_design_scores_gemma":[0.002507407,0.0009443283,0.02792533,0.0003591173,0.00006821597,0.0001201278,0.0009646405,0.8711803,0.01588682,0.0772147,0.002451581,0.000377431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1101905,0.00009910312,0.8878676,0.0009494704,0.0001786117,0.0002150648,0.000002059988,0.00006938398,0.0004283173],"genre_scores_gemma":[0.7946717,0.0004214008,0.2043172,0.0001494024,0.0001920072,0.0000218118,0.00009281447,0.00001060724,0.0001231383],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8656936,"threshold_uncertainty_score":0.2962902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05249424612086351,"score_gpt":0.4009384216784216,"score_spread":0.3484441755575581,"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."}}