{"id":"W4399669692","doi":"10.1080/17686733.2024.2364961","title":"Enhancing thermal facial recognition leveraging large datasets and hybrid algorithms","year":2024,"lang":"en","type":"article","venue":"Quantitative InfraRed Thermography Journal","topic":"Face recognition and analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"National Natural Science Foundation of China","keywords":"Computer science; Facial recognition system; Face (sociological concept); Artificial intelligence; Feature (linguistics); Feature extraction; Set (abstract data type); Pattern recognition (psychology); Scale (ratio); Image (mathematics); Function (biology); Fusion; Algorithm; Computer vision","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009399836,0.0002296031,0.0002355263,0.0007979091,0.0004950474,0.001230002,0.0003473545,0.00004994149,0.0002207575],"category_scores_gemma":[0.00005830593,0.0001956501,0.0002468139,0.0008328812,0.00008364904,0.001787152,0.0001127019,0.0005159923,0.0000836521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002611849,"about_ca_system_score_gemma":0.00007595462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006153245,"about_ca_topic_score_gemma":0.000003003872,"domain_scores_codex":[0.998129,0.0002754366,0.0003965901,0.000419351,0.000372162,0.0004075241],"domain_scores_gemma":[0.9991322,0.0002238572,0.0001343376,0.0001781478,0.0001432357,0.0001882863],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003909711,0.0001632331,0.0005000354,0.00009567977,0.001135891,0.0009439251,0.008650274,0.00002111498,0.02700526,0.004796319,0.001927046,0.9547221],"study_design_scores_gemma":[0.006275966,0.001782313,0.01680372,0.004061171,0.0008705205,0.004872073,0.01239696,0.5036001,0.08088557,0.3088928,0.05462937,0.00492939],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1858387,0.003693925,0.8077149,0.0004150069,0.0006621123,0.0001162711,0.0004441983,0.0002164883,0.0008984734],"genre_scores_gemma":[0.9288317,0.0008794987,0.06908614,0.0006172455,0.0002860592,0.00001585142,0.0001853349,0.00003861487,0.00005952991],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9497927,"threshold_uncertainty_score":0.9998068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02832125303583989,"score_gpt":0.2831907922368073,"score_spread":0.2548695392009674,"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."}}