{"id":"W2911662480","doi":"10.1007/978-3-030-11015-4_55","title":"Increasing the Robustness of CNN-Based Human Body Segmentation in Range Images by Modeling Sensor-Specific Artifacts","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Computer vision; Segmentation; Range (aeronautics); Image segmentation; Pattern recognition (psychology)","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"],"consensus_categories":[],"category_scores_codex":[0.001195279,0.0003431479,0.0003853225,0.0007560835,0.0002382733,0.000430328,0.001298715,0.000186489,0.0000264089],"category_scores_gemma":[0.00002947033,0.0002839133,0.00009696447,0.0004845169,0.0002831517,0.000665718,0.0002572433,0.0005768679,0.00001693057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002181333,"about_ca_system_score_gemma":0.000209889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007030231,"about_ca_topic_score_gemma":0.00003821274,"domain_scores_codex":[0.9971946,0.0001161714,0.000580995,0.000886019,0.0008266385,0.0003955398],"domain_scores_gemma":[0.9981647,0.0004311591,0.0003528067,0.0007450295,0.0002432125,0.00006315319],"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":[0.00001600633,0.00006263775,0.000152444,0.00007303371,0.000007621163,0.00001470548,0.0005228906,0.8460069,0.01607355,0.0006589582,0.0000249534,0.1363863],"study_design_scores_gemma":[0.00043485,0.00006857415,0.0001307053,0.0004705752,0.000005787585,0.00001344259,0.00000135259,0.9800988,0.01438131,0.003988592,0.00004228401,0.0003636627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03075366,0.0001798134,0.9671826,0.0002959908,0.0005567446,0.0004679291,0.000006464693,0.00005714509,0.0004996348],"genre_scores_gemma":[0.9489883,0.00002560822,0.05031022,0.0003793272,0.0001736822,0.00000740055,0.00002336468,0.00002483247,0.0000673379],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9182346,"threshold_uncertainty_score":0.9999613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02620336246998232,"score_gpt":0.2540230648703793,"score_spread":0.227819702400397,"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."}}