{"id":"W4366999328","doi":"10.48550/arxiv.2304.11291","title":"VisiTherS: Visible-thermal infrared stereo disparity estimation of human silhouette","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Infrared Thermography in Medicine","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Silhouette; Convolutional neural network; Concatenation (mathematics); Computer vision; Feature (linguistics); Matching (statistics); Thermal infrared; Pattern recognition (psychology); Infrared; Task (project management); Pixel; Mathematics; Optics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004936163,0.0005121261,0.0009823797,0.0009339314,0.0001424671,0.0000257875,0.0006077842,0.0006295083,0.0003203852],"category_scores_gemma":[0.000105532,0.0005533876,0.0004895584,0.0009914133,0.0004413262,0.0001749775,0.0006594273,0.001158198,0.00009039781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002340831,"about_ca_system_score_gemma":0.0001986453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003026101,"about_ca_topic_score_gemma":0.00002013635,"domain_scores_codex":[0.9975232,0.0001830637,0.0005782693,0.0009397069,0.0002974725,0.0004782386],"domain_scores_gemma":[0.9970361,0.0001456588,0.0006313085,0.001597323,0.0003179204,0.0002717199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.004343745,0.002673336,0.4264389,0.0121635,0.007422571,0.005853079,0.007148893,0.4513496,0.0283787,0.04285788,0.006478897,0.004890937],"study_design_scores_gemma":[0.01276413,0.002109523,0.6721582,0.007688312,0.005287032,0.00003580136,0.001712075,0.2142341,0.007226714,0.0742072,0.0001925247,0.002384397],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9865241,0.00008989087,0.006321371,0.000105376,0.0004758299,0.0009570941,0.0000919194,0.0004654637,0.004968971],"genre_scores_gemma":[0.9954774,0.00009211704,0.0004668304,0.0001439605,0.000210377,0.000003618455,0.0003708969,0.0001011413,0.003133614],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2457193,"threshold_uncertainty_score":0.9996918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07689321091618172,"score_gpt":0.2408746804893473,"score_spread":0.1639814695731656,"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."}}