{"id":"W3096175651","doi":"10.1109/access.2020.3034386","title":"Detecting 6D Poses of Target Objects From Cluttered Scenes by Learning to Align the Point Cloud Patches With the CAD Models","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Point cloud; Computer science; Robustness (evolution); Artificial intelligence; Computer vision; Object detection; CAD; Cloud computing; Object (grammar); Automation; Key (lock); Cognitive neuroscience of visual object recognition; Segmentation; Engineering; Engineering drawing","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":[0.0001385371,0.0001601254,0.000186592,0.00002671546,0.0001726027,0.0001485476,0.0004112559,0.00004622185,0.00003461344],"category_scores_gemma":[0.00005046222,0.00009891493,0.00004326384,0.0002350431,0.00002305497,0.0002637884,0.00005983429,0.000293096,0.00001119921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001737694,"about_ca_system_score_gemma":0.00001157434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005169944,"about_ca_topic_score_gemma":0.00008988137,"domain_scores_codex":[0.9991046,0.00009761051,0.0001993554,0.0001866221,0.0002030047,0.0002088704],"domain_scores_gemma":[0.9994198,0.0002109773,0.00008253597,0.0001752692,0.00004287418,0.00006850973],"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":[0.00002330731,0.000003037379,0.001509992,0.00002098459,0.00004702516,0.00000206337,0.01055703,0.969145,0.01698862,0.000004359519,0.001013567,0.000685028],"study_design_scores_gemma":[0.0002993186,0.00006331273,0.001910601,0.0000712312,0.00003344685,0.000001882229,0.003894225,0.876187,0.1166572,0.0001267463,0.0004799926,0.0002749848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8630868,0.0002560469,0.1345108,0.001281304,0.0001407148,0.0002016065,0.000002870291,0.0002008182,0.0003190521],"genre_scores_gemma":[0.9986287,0.000008130612,0.0003831323,0.0006753418,0.0002194099,0.00001521195,0.000005262602,0.00004621149,0.00001855732],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.135542,"threshold_uncertainty_score":0.4033633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0348878739953094,"score_gpt":0.2369061289691042,"score_spread":0.2020182549737948,"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."}}