{"id":"W4405907349","doi":"10.1109/lra.2024.3520436","title":"Targeted Hard Sample Synthesis Based on Estimated Pose and Occlusion Error for Improved Object Pose Estimation","year":2024,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dynamic Systems Analysis (Canada); University of Toronto","funders":"","keywords":"Pose; Estimation; Artificial intelligence; Sample (material); Object (grammar); Computer science; Computer vision; 3D pose estimation; Pattern recognition (psychology); Engineering; Chemistry; Chromatography","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":[0.0001698575,0.0001815032,0.0001624201,0.0002329853,0.0001549323,0.0002237166,0.00004040506,0.00007954967,0.00001717882],"category_scores_gemma":[0.0001424861,0.0001784405,0.00004608767,0.0001532922,0.00002075403,0.000199477,0.000007169277,0.0001095893,0.000007581791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005990808,"about_ca_system_score_gemma":0.00001218558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001015958,"about_ca_topic_score_gemma":0.000001589287,"domain_scores_codex":[0.9992285,0.00002922615,0.0002339667,0.0002225139,0.0001055623,0.0001802355],"domain_scores_gemma":[0.9993226,0.0004370741,0.00003886584,0.0001106566,0.00002546035,0.00006537272],"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":[0.00001051565,0.000007130935,0.00003218092,0.0002262992,0.00002069166,0.000001896954,0.0001220222,0.9403775,0.04992871,0.00009349357,0.001008323,0.008171199],"study_design_scores_gemma":[0.0002563723,0.0000358145,0.003518417,0.0002001642,0.00004805039,0.000003583707,0.000008858021,0.993105,0.00244186,0.00005965175,0.0001146115,0.0002076042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07618143,0.00007348696,0.9188798,0.002920834,0.0006855315,0.0003701398,0.00001995665,0.0008528138,0.00001600141],"genre_scores_gemma":[0.9161009,0.000008829384,0.0832162,0.0004043618,0.00007508404,0.00002555815,0.0001098825,0.00004910449,0.00001007195],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8399194,"threshold_uncertainty_score":0.7276591,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01974924692731886,"score_gpt":0.2520500083984356,"score_spread":0.2323007614711168,"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."}}