{"id":"W1988539193","doi":"10.1007/s00138-011-0353-9","title":"Three-dimensional human shape inference from silhouettes: reconstruction and validation","year":2011,"lang":"en","type":"article","venue":"Machine Vision and Applications","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":42,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Silhouette; Artificial intelligence; Computer vision; Computer science; Body shape; Prior probability; Inference; Mathematics; Principal component analysis; Image (mathematics); Pattern recognition (psychology); Shape analysis (program analysis); Geometric shape; Bayesian probability; Geometry","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":[0.00005500815,0.00009669997,0.00009924253,0.00007302532,0.000160894,0.00003058989,0.0000459907,0.0000478111,0.0002230192],"category_scores_gemma":[0.000004026743,0.00008645936,0.0000216002,0.0001008646,0.00003551678,0.00008462026,0.00002542043,0.00008935703,0.00001896349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006523588,"about_ca_system_score_gemma":0.00000259208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002169518,"about_ca_topic_score_gemma":0.0000793796,"domain_scores_codex":[0.9995208,0.00000703791,0.0001547426,0.0001796253,0.00006465449,0.00007309562],"domain_scores_gemma":[0.9997261,0.00002824024,0.00002607876,0.0001352472,0.00002463647,0.00005965266],"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":[0.000006241285,0.00008688075,0.02950237,0.00003374747,0.00008464076,5.835159e-7,0.000269916,0.003583767,0.0258563,0.003939918,0.0002165135,0.9364191],"study_design_scores_gemma":[0.000179058,0.00001664964,0.01926334,0.00002428637,0.00004574769,0.000002872561,0.00001484824,0.9668003,0.001014034,0.01217542,0.000302409,0.0001610576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8256534,0.0003575977,0.1726673,0.00005125559,0.0000212086,0.0001030806,0.00003307319,0.0001920229,0.000920986],"genre_scores_gemma":[0.9955105,0.00005847456,0.004217541,0.00002895443,0.00004259217,0.00003289834,0.00008712599,0.00001120969,0.00001076252],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9632165,"threshold_uncertainty_score":0.352571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02192251718407639,"score_gpt":0.2549253261418103,"score_spread":0.2330028089577339,"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."}}