{"id":"W4284884302","doi":"10.3390/jimaging8070188","title":"Efficient and Scalable Object Localization in 3D on Mobile Device","year":2022,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Computer vision; Augmented reality; Mobile device; Leverage (statistics); Object (grammar); Object detection; Minimum bounding box; Convolutional neural network; Scalability; Pose; Pattern recognition (psychology); Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001703649,0.0009104233,0.0006293185,0.0007864014,0.0003333875,0.0008666492,0.001055696,0.0006495416,0.0031412],"category_scores_gemma":[0.0006074414,0.0004538385,0.0006323821,0.0006967082,0.000299209,0.001212042,0.00165381,0.0004296445,0.002115175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003995569,"about_ca_system_score_gemma":0.0005175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005152652,"about_ca_topic_score_gemma":0.009279767,"domain_scores_codex":[0.9997048,0.00002394011,0.000009988274,0.00008284207,0.0001346584,0.0000437774],"domain_scores_gemma":[0.9997739,0.00004137524,0.0000233678,0.00007647809,0.00006795994,0.00001698202],"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":[0.0003598697,0.0001376757,0.003220105,0.0002745172,0.0001144732,0.0006588491,0.000280714,0.1084081,0.1373485,0.004806348,0.01493426,0.7294566],"study_design_scores_gemma":[0.00002312697,0.0001016838,0.001921661,0.00002728586,0.00002305852,0.0003913671,0.0001266447,0.9529607,0.03078284,0.003342239,0.0102627,0.00003662983],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03081616,0.0003075435,0.9575787,0.0001177588,0.00007313874,0.00006176475,0.000264833,0.007716405,0.003063662],"genre_scores_gemma":[0.4471037,0.0004496688,0.5452851,0.0001733679,0.00005061139,0.0001489016,0.001079078,0.0003495078,0.005359994],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005152652,"threshold_uncertainty_score":0.01050836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005015111700132593,"score_gpt":0.2083085249919523,"score_spread":0.2032934132918198,"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."}}