{"id":"W6910129058","doi":"10.48336/70bt-e804","title":"Deep learning based auto-labeling for sparse underwater freestyle marker-based optical motion capture using Qualisys Miqus M5U MoCap cameras","year":2025,"lang":"en","type":"article","venue":"Memorial University Research Repository (Memorial University)","topic":"Underwater Vehicles and Communication Systems","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Motion capture; Convolutional neural network; Ground truth; Process (computing); Pattern recognition (psychology); Principal component analysis; Set (abstract data type); Data set; Deep learning","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001201481,0.0003818109,0.0005220543,0.001279252,0.00181383,0.0002950357,0.001125151,0.0005310932,0.00003105399],"category_scores_gemma":[0.00007146184,0.0004722602,0.0003045064,0.001415763,0.0003133187,0.0005334892,0.0003171948,0.001068118,0.00001336825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002080047,"about_ca_system_score_gemma":0.0005533643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001830845,"about_ca_topic_score_gemma":0.0003619346,"domain_scores_codex":[0.9960786,0.001269715,0.0003933006,0.000675603,0.000709341,0.00087348],"domain_scores_gemma":[0.9974054,0.0006295999,0.0001113264,0.0007323213,0.0007992555,0.0003221184],"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":[0.00391939,0.0005651457,0.002118595,0.001083564,0.0008070695,0.0006733619,0.001045154,0.6185063,0.3656409,0.002867285,0.001162358,0.001610904],"study_design_scores_gemma":[0.007079964,0.0002118492,0.0001370206,0.0003412039,0.0003035383,0.000007267097,0.00498343,0.8394469,0.05196642,0.00008717947,0.0946632,0.0007720425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3600223,0.0001259011,0.6214412,0.0002875131,0.003351326,0.001614717,0.00002955931,0.0008216536,0.01230578],"genre_scores_gemma":[0.9859946,0.00002006908,0.006404393,0.00001466495,0.0009303417,0.000002234799,0.00007897022,0.00005994326,0.006494761],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6259723,"threshold_uncertainty_score":0.9997729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03710268996145893,"score_gpt":0.2608808852180455,"score_spread":0.2237781952565866,"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."}}