{"id":"W1999160991","doi":"10.1111/j.1467-8659.2009.01418.x","title":"Semi‐Supervised Learning in Reconstructed Manifold Space for 3D Caricature Generation","year":2009,"lang":"en","type":"article","venue":"Computer Graphics Forum","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Regularization (linguistics); Principal component analysis; Set (abstract data type); Manifold (fluid mechanics); 3d model; Machine learning; Pattern recognition (psychology); Computer vision","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":[],"consensus_categories":[],"category_scores_codex":[0.0001920731,0.0001679829,0.0001788101,0.0003727902,0.0002314906,0.0002290378,0.0003372795,0.0001673221,0.000005355956],"category_scores_gemma":[0.00001167302,0.0001764558,0.0001044995,0.0005686,0.00001422696,0.0005201508,0.00005435149,0.0003402444,0.000008888032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003295302,"about_ca_system_score_gemma":0.00004826591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006509967,"about_ca_topic_score_gemma":0.00004356448,"domain_scores_codex":[0.9987398,0.00006897308,0.0002594072,0.0004374697,0.0001517361,0.0003425543],"domain_scores_gemma":[0.9993711,0.00005494836,0.0001007515,0.00027273,0.0001273859,0.00007316231],"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":[0.0000201394,0.000190997,0.003705603,0.00003331485,0.00003915726,0.00002350452,0.0008965143,0.0009684692,0.002699167,0.4200783,0.01202575,0.559319],"study_design_scores_gemma":[0.0007623863,0.0002575795,0.003729791,0.00003919071,0.000006854458,0.00003035427,0.00001570646,0.9715809,0.0009921216,0.01030298,0.01199271,0.0002894257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04512812,0.0001019751,0.9503099,0.00282441,0.0006702319,0.0003434895,0.000002894764,0.0002764915,0.0003424287],"genre_scores_gemma":[0.8921297,0.00006507006,0.1047285,0.002496669,0.00035818,0.00002361622,0.00009122519,0.00001316984,0.0000938593],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9706124,"threshold_uncertainty_score":0.7195657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01827952165828422,"score_gpt":0.2329914342788642,"score_spread":0.21471191262058,"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."}}