{"id":"W2894703649","doi":"10.1016/j.neucom.2018.09.075","title":"NormalNet: A voxel-based CNN for 3D object classification and retrieval","year":2018,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":155,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Concatenation (mathematics); Voxel; Artificial intelligence; Object (grammar); Pattern recognition (psychology); Cognitive neuroscience of visual object recognition; Convolutional neural network; Computer vision; Projection (relational algebra); Mathematics; Algorithm","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":[0.000224621,0.00009344443,0.00008747302,0.00009980203,0.0003545835,0.0001753056,0.0001824,0.0000438951,0.000005311907],"category_scores_gemma":[0.00006077758,0.00009519021,0.0000353615,0.0002056158,0.00004207584,0.0002297378,0.0000555899,0.00008437948,0.00003708931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001469978,"about_ca_system_score_gemma":0.00003851083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001969961,"about_ca_topic_score_gemma":0.000001519574,"domain_scores_codex":[0.9991184,0.00004370898,0.0001750338,0.0003430636,0.0001199427,0.0001998878],"domain_scores_gemma":[0.9993516,0.0001615472,0.00010887,0.0001847571,0.0001368785,0.00005638147],"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":[0.00009684281,0.0001393806,0.001602463,0.000120343,0.00001812757,0.000006695751,0.0009870483,0.00007208916,0.03404884,0.005396498,0.002000093,0.9555116],"study_design_scores_gemma":[0.0005638916,0.0002933097,0.01305992,0.00002680652,0.000006602306,0.00001275665,0.000008667449,0.9623775,0.01172845,0.0004722014,0.0113004,0.0001494716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2252107,0.000008041752,0.7720368,0.000390986,0.0003747813,0.0002477109,0.000001171577,0.0002102538,0.001519558],"genre_scores_gemma":[0.953992,9.011962e-7,0.04437885,0.001083675,0.0004793876,0.000005651466,0.000004166312,0.000009273628,0.0000460923],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9623054,"threshold_uncertainty_score":0.3881744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0352415215578013,"score_gpt":0.2774629709891423,"score_spread":0.242221449431341,"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."}}