{"id":"W2885236043","doi":"10.1016/j.neucom.2018.07.061","title":"SliceNet: A proficient model for real-time 3D shape-based recognition","year":2018,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Computer science; Convolution (computer science); Artificial intelligence; Variance (accounting); Feature (linguistics); Object (grammar); Pattern recognition (psychology); Kernel (algebra); Inference; Cognitive neuroscience of visual object recognition; Independence (probability theory); Computer vision; Mathematics; Artificial neural network; Statistics","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":[0.0002533974,0.0001328029,0.0001444512,0.00010617,0.0001749672,0.00005300967,0.00006611249,0.0001024138,0.00001891375],"category_scores_gemma":[0.00003579558,0.0001358545,0.00006888201,0.0001767429,0.00001230246,0.00005224814,0.00001421422,0.0000975483,0.0001216566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004642522,"about_ca_system_score_gemma":0.00002036409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009444609,"about_ca_topic_score_gemma":0.000001616545,"domain_scores_codex":[0.9990863,0.00002550504,0.0002674798,0.000226355,0.0001299593,0.0002644402],"domain_scores_gemma":[0.9995597,0.00007861191,0.00005812914,0.0001323809,0.000117399,0.00005378164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000104201,0.000041714,0.00002878574,0.0001550746,0.00001750366,0.000002155877,0.0003736691,0.4545242,0.2492042,0.00001207959,0.002790278,0.2927461],"study_design_scores_gemma":[0.0004905258,0.000147123,0.00003779884,0.00006177653,0.000008738388,0.00000343132,0.000004793664,0.9789809,0.01905521,0.0000177876,0.001047711,0.0001441868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7561602,0.000003872497,0.2386041,0.00001194461,0.0006733383,0.0006966359,0.00001111969,0.0007176861,0.00312107],"genre_scores_gemma":[0.9923028,4.35606e-7,0.006484592,0.00007255637,0.0009762655,0.00004462634,0.0000102298,0.00005013546,0.00005841319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5244567,"threshold_uncertainty_score":0.5539985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04069164153942346,"score_gpt":0.2516258020895056,"score_spread":0.2109341605500821,"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."}}