{"id":"W2920519816","doi":"10.1117/12.2508903","title":"Training a CNN to robustly segment the human body parts in range image sequences","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Optical Sensing Technologies","field":"Physics and Astronomy","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Artificial intelligence; Computer vision; Computer science; Robustness (evolution); Segmentation; Structured light; Noise (video); Image segmentation; Projector; Image sensor; Image (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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011104,0.0001023421,0.0001355618,0.00003189271,0.00006183155,0.00004410187,0.0001860279,0.00002168773,0.0002960337],"category_scores_gemma":[0.000009657383,0.0000652696,0.00003666374,0.0001338545,0.0000597458,0.00009032554,0.00009708969,0.0001409327,0.0001157558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002363073,"about_ca_system_score_gemma":0.00001062819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002023434,"about_ca_topic_score_gemma":0.00002876822,"domain_scores_codex":[0.9992832,0.00001754063,0.0001368888,0.000196981,0.0000977976,0.0002675874],"domain_scores_gemma":[0.9996082,0.00007028535,0.0000284546,0.0002476505,0.00001576581,0.00002966891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002658177,0.0002307166,0.1006501,0.00001593046,0.00008731657,0.00002025067,0.004061237,0.008014794,0.09942291,0.6765747,0.0012752,0.1096202],"study_design_scores_gemma":[0.005027085,0.001192654,0.1156058,0.0006014638,0.00009141955,0.00000679988,0.07925772,0.0136605,0.1606162,0.5829026,0.0376815,0.003356232],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9495433,0.000004994953,0.008148211,0.001776231,0.00004688419,0.0003502448,0.000002580939,0.0001106949,0.04001687],"genre_scores_gemma":[0.9833018,1.959981e-7,0.015771,0.0001250077,0.0000361878,0.00001940082,0.000002253333,0.000008597064,0.0007355301],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.106264,"threshold_uncertainty_score":0.3241361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0304221334088551,"score_gpt":0.2913212776639192,"score_spread":0.2608991442550642,"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."}}