{"id":"W4402455728","doi":"10.1145/3695877","title":"Category-Level Pose Estimation and Iterative Refinement for Monocular RGB-D Image","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Computer vision; Monocular; Pose; RGB color model","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":[0.0001542672,0.000183574,0.0001490219,0.0001898447,0.0005848311,0.0001981566,0.0002470851,0.00007960417,0.000007194658],"category_scores_gemma":[0.00001696526,0.0001935012,0.0000530793,0.0002875611,0.0001225663,0.0001337241,0.00002085796,0.0002151843,0.00001300295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000058068,"about_ca_system_score_gemma":0.00002246521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002470506,"about_ca_topic_score_gemma":0.0000191709,"domain_scores_codex":[0.9991383,0.00003335277,0.0003147732,0.0002614195,0.00008626578,0.000165867],"domain_scores_gemma":[0.9983048,0.0006626569,0.00003136979,0.0008113607,0.0001006973,0.0000891411],"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":[0.00000452883,0.0001239751,0.000006386778,0.0001956903,0.000115218,3.090386e-7,0.001158414,0.1058156,0.003797574,0.005617643,0.0002438591,0.8829208],"study_design_scores_gemma":[0.0002573685,0.00003544357,0.00008961924,0.00006963039,0.00007782409,0.000005247159,0.0001364476,0.9869915,0.0008707285,0.001774473,0.009497858,0.0001938524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001244052,0.001062553,0.9944973,0.001586386,0.00008483235,0.0008338816,0.0001511535,0.0003737648,0.0001661046],"genre_scores_gemma":[0.5822685,0.0009273161,0.4159689,0.00005272652,0.00003892706,0.0004029456,0.0002609257,0.0000373777,0.00004243496],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.882727,"threshold_uncertainty_score":0.7890751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02854752951188997,"score_gpt":0.2878520545801899,"score_spread":0.2593045250682999,"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."}}