{"id":"W4383108938","doi":"10.1109/icra48891.2023.10160354","title":"Multi-View Keypoints for Reliable 6D Object Pose Estimation","year":2023,"lang":"en","type":"article","venue":"","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dynamic Systems Analysis (Canada); Vector Institute; University of Toronto","funders":"Epson","keywords":"Artificial intelligence; Pose; Computer science; Point cloud; Feature (linguistics); Computer vision; Object (grammar); 3D pose estimation; Pattern recognition (psychology); False positive paradox; Object detection; Point (geometry); Mathematics","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":[0.001223725,0.002344664,0.002152848,0.00378501,0.0004919486,0.001895858,0.003100876,0.001940175,0.005666718],"category_scores_gemma":[0.006019386,0.001141661,0.001249967,0.003154627,0.0006531078,0.0029319,0.004441636,0.002123093,0.007127911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005298675,"about_ca_system_score_gemma":0.0006574055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00264391,"about_ca_topic_score_gemma":0.005113358,"domain_scores_codex":[0.9969276,0.0002869236,0.0001048916,0.0008098483,0.001601148,0.000269584],"domain_scores_gemma":[0.9978145,0.0003175557,0.000224815,0.0008538422,0.0006869585,0.0001023595],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005812321,0.0001854462,0.003684185,0.0006073337,0.0003482445,0.0004191765,0.000262198,0.0784348,0.07575615,0.005735259,0.02582783,0.8081582],"study_design_scores_gemma":[0.00006378945,0.0002726591,0.006884216,0.000139468,0.00008074784,0.001571557,0.0002125881,0.8638479,0.08358546,0.01411567,0.02910912,0.0001169769],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009593426,0.001030572,0.9780286,0.00009360543,0.0001351437,0.00008818493,0.001084247,0.008945788,0.001000456],"genre_scores_gemma":[0.3310809,0.001185893,0.6544682,0.0002036059,0.0001741633,0.0002434306,0.008504695,0.001131609,0.003007629],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005666718,"threshold_uncertainty_score":0.01895702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02443298518174388,"score_gpt":0.2577481943616357,"score_spread":0.2333152091798918,"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."}}