{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004990068,0.001293701,0.001091392,0.00155409,0.0004010707,0.000582471,0.002162896,0.0007686796,0.002698494],"category_scores_gemma":[0.001775059,0.0006067993,0.0009238639,0.001366726,0.0005369636,0.001030917,0.001349369,0.0009877081,0.002407867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006741362,"about_ca_system_score_gemma":0.001363343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01631936,"about_ca_topic_score_gemma":0.02698685,"domain_scores_codex":[0.999283,0.00005702491,0.00002853738,0.0002819785,0.0002587845,0.00009062583],"domain_scores_gemma":[0.9992925,0.0001030956,0.00007741768,0.0001955948,0.0002882905,0.0000430704],"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":[0.0001610261,0.00011286,0.002787599,0.0000951513,0.00006026621,0.00008403642,0.0001335935,0.06462287,0.03479313,0.002665838,0.004799704,0.8896839],"study_design_scores_gemma":[0.0000186386,0.0001517612,0.003145051,0.00001568713,0.00003063703,0.0002208607,0.000049094,0.9595965,0.02728236,0.004533999,0.004917431,0.00003797364],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00953748,0.000179219,0.9857943,0.00003899774,0.00003587946,0.00006544235,0.0001421912,0.00340731,0.0007991743],"genre_scores_gemma":[0.3058814,0.0003811409,0.6827795,0.0001875958,0.00007813351,0.0002262501,0.002258314,0.0004102879,0.007797303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01631936,"threshold_uncertainty_score":0.03244877,"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."}}