{"id":"W2765872781","doi":"10.1109/avss.2017.8078553","title":"Using deep autoencoders to learn robust domain-invariant representations for still-to-video face recognition","year":2017,"lang":"en","type":"article","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Autoencoder; Computer vision; Facial recognition system; Face (sociological concept); Pattern recognition (psychology); Facial expression; Video quality; Matching (statistics); Deep learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005100824,0.001039171,0.0005576222,0.0004527103,0.0001736115,0.0004061725,0.00106559,0.0007221503,0.00139742],"category_scores_gemma":[0.001155028,0.0004132261,0.0005840131,0.0003756681,0.0003704666,0.0008475416,0.0005741912,0.001169974,0.0008696338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005621974,"about_ca_system_score_gemma":0.0005764955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007300193,"about_ca_topic_score_gemma":0.009710439,"domain_scores_codex":[0.9997105,0.00003602041,0.0000117241,0.0001107915,0.00008430119,0.00004674416],"domain_scores_gemma":[0.9997219,0.00008381739,0.00003857709,0.00006655385,0.00007441618,0.000014642],"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":[0.0002029961,0.0001964868,0.00147979,0.0001026726,0.0001868979,0.0001613698,0.00005312766,0.3333198,0.0478159,0.003240927,0.004960775,0.6082793],"study_design_scores_gemma":[0.000003241795,0.00003196935,0.0003859444,0.000005451372,0.00001284127,0.00002950949,0.000006060249,0.9926514,0.005504646,0.000762435,0.0006005986,0.000005884234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05524754,0.0009870616,0.9384347,0.0001450739,0.0001226967,0.00006352558,0.0002255847,0.002676214,0.002097647],"genre_scores_gemma":[0.6831739,0.001054652,0.3048042,0.0003678902,0.0001009626,0.0001284528,0.001617887,0.0001951444,0.008556923],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007300193,"threshold_uncertainty_score":0.0145154,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1184309926371423,"score_gpt":0.3402313567947307,"score_spread":0.2218003641575884,"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."}}