{"id":"W4386923660","doi":"10.2139/ssrn.4579060","title":"Enhancing Voxel Transformer with Spatial-Semantic Feature Aggregation and Optimized Rpn for 3d Object Detection","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Voxel; Transformer; Computer science; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Computer vision; Object (grammar); Object based; Engineering; Voltage; Electrical engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006513995,0.0009482616,0.001002967,0.0009367164,0.0002773667,0.001090918,0.001230708,0.0008833733,0.004113297],"category_scores_gemma":[0.001658909,0.0005215498,0.0008992459,0.001264801,0.0003380895,0.001273067,0.001468978,0.0009126994,0.001728868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004875626,"about_ca_system_score_gemma":0.001194786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00371022,"about_ca_topic_score_gemma":0.006801792,"domain_scores_codex":[0.9996468,0.00005042671,0.00001858966,0.00009246296,0.00013847,0.00005325924],"domain_scores_gemma":[0.9996367,0.00009512825,0.00002517945,0.00009207932,0.0001286441,0.00002230431],"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":[0.0005750014,0.0001687888,0.001223645,0.0001782925,0.0001279911,0.0001750913,0.00007716323,0.08570622,0.0913555,0.008568821,0.006889165,0.8049543],"study_design_scores_gemma":[0.0000133001,0.0000544201,0.0005702093,0.00001069521,0.00004213895,0.0002016981,0.00002254574,0.9587285,0.03168958,0.006232787,0.002419935,0.00001419409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00984179,0.000191477,0.9869937,0.00006898175,0.00005045697,0.00003163384,0.0001657332,0.001740761,0.0009153204],"genre_scores_gemma":[0.253348,0.0003063634,0.7412242,0.0001767598,0.00006059193,0.00008491727,0.0008792668,0.0004901461,0.003429659],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004113297,"threshold_uncertainty_score":0.01376033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01012712021134749,"score_gpt":0.2492821585003202,"score_spread":0.2391550382889727,"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."}}