{"id":"W2613081229","doi":"10.1016/j.patrec.2017.05.011","title":"Deep learning with geodesic moments for 3D shape classification","year":2017,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":46,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Geodesic; Softmax function; Artificial intelligence; Pattern recognition (psychology); Computer science; Deep learning; Mathematics; Autoencoder; Inverse; Eigenvalues and eigenvectors; Algorithm; 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":[0.00009921089,0.0001311512,0.0001264004,0.00008355264,0.000304172,0.0001590563,0.0001274372,0.00004250409,0.00007710563],"category_scores_gemma":[0.00001805342,0.0001272052,0.00006014549,0.00002933298,0.00002511424,0.0002048275,0.000009237938,0.0001239234,0.000118757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004007356,"about_ca_system_score_gemma":0.000002284513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001230338,"about_ca_topic_score_gemma":0.00001290718,"domain_scores_codex":[0.999317,0.00001416224,0.0001458856,0.0001960108,0.0001185022,0.000208386],"domain_scores_gemma":[0.9995988,0.00002735377,0.00008495395,0.0001944747,0.00004617753,0.00004821363],"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":[0.00001290721,0.00001663064,0.01332385,0.0001038555,0.0001592398,0.000003728794,0.000186792,0.03612119,0.005472282,2.329123e-7,0.0002372188,0.944362],"study_design_scores_gemma":[0.0004515039,0.00001992345,0.007101895,0.00006856245,0.00007881573,0.000001882674,0.000042427,0.9913815,0.0003954047,0.00001581038,0.0002317584,0.0002105074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.423586,0.00001040412,0.5754299,0.0004541283,0.00007479003,0.00009563566,0.000007062049,0.0001312987,0.0002107573],"genre_scores_gemma":[0.9962329,0.00002602745,0.002814454,0.0003991251,0.0001475753,0.0001190264,0.0001869818,0.00004226074,0.00003166957],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9552603,"threshold_uncertainty_score":0.5187276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03797523058152084,"score_gpt":0.2400378682532533,"score_spread":0.2020626376717325,"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."}}