{"id":"W2999734205","doi":"10.3390/s20020543","title":"Hybrid Eye-Tracking on a Smartphone with CNN Feature Extraction and an Infrared 3D Model","year":2020,"lang":"en","type":"article","venue":"Sensors","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Huawei Technologies","keywords":"Computer vision; Artificial intelligence; Computer science; Eye tracking; BitTorrent tracker; Robustness (evolution); Gaze; Convolutional neural network; Feature extraction; Mobile device; Feature (linguistics); Tracking system; Kalman filter","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001376391,0.0005254621,0.0003656327,0.0003921201,0.0001143768,0.0003300759,0.0004914927,0.0003726025,0.001826365],"category_scores_gemma":[0.0003763452,0.0002596846,0.0004795518,0.0002602862,0.00007855728,0.0003304695,0.0004126246,0.000276923,0.0006798028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004122433,"about_ca_system_score_gemma":0.0003286203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01050124,"about_ca_topic_score_gemma":0.01826221,"domain_scores_codex":[0.9998676,0.000007852387,0.000005688524,0.00004962918,0.00005187491,0.00001732434],"domain_scores_gemma":[0.9998999,0.00001705421,0.00001321531,0.00001872581,0.00004495924,0.000006230818],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004497702,0.0001448366,0.007854417,0.0002246245,0.0002365533,0.0004372277,0.0001312152,0.06899168,0.2685834,0.0008222057,0.005496779,0.6466274],"study_design_scores_gemma":[0.00001826063,0.0001406203,0.01032659,0.00002610112,0.00005493577,0.0003665682,0.00002034402,0.9359108,0.04925925,0.0003881381,0.003452901,0.00003545591],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2055814,0.0009230177,0.7799098,0.0002364244,0.0001524088,0.0001453105,0.001149085,0.006833752,0.005068867],"genre_scores_gemma":[0.7451302,0.0004960229,0.2446177,0.0002424896,0.00004238062,0.0001372212,0.001079083,0.0001698805,0.008084995],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01050124,"threshold_uncertainty_score":0.02088022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01997847443780336,"score_gpt":0.2658559093776635,"score_spread":0.2458774349398601,"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."}}