{"id":"W2888761084","doi":"10.3390/vision2030035","title":"Accurate Model-Based Point of Gaze Estimation on Mobile Devices","year":2018,"lang":"en","type":"article","venue":"Vision","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Gaze; Computer vision; Computer science; Offset (computer science); Artificial intelligence; Eye tracking; Mobile device; Point (geometry); Tracking (education); Mathematics; Geometry","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":[0.0003706626,0.0005885785,0.0009070604,0.0007054083,0.0002873194,0.0006814097,0.0005906525,0.0005556928,0.001553782],"category_scores_gemma":[0.002520002,0.0003698155,0.0004969836,0.0005386421,0.000156735,0.001097524,0.0007442385,0.0005092667,0.0009647024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004567306,"about_ca_system_score_gemma":0.0004515137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009126189,"about_ca_topic_score_gemma":0.01132218,"domain_scores_codex":[0.9994209,0.0001063176,0.00003075599,0.0001495888,0.0002469409,0.00004546659],"domain_scores_gemma":[0.9992688,0.0001647792,0.00008729201,0.0001837556,0.0002737287,0.00002152912],"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":[0.0008074857,0.0001893941,0.01867019,0.00059663,0.0003020581,0.0004503297,0.000611514,0.2122335,0.2542114,0.002175479,0.005254039,0.5044979],"study_design_scores_gemma":[0.00003977054,0.000228898,0.02031272,0.00006298963,0.00004734531,0.0003690857,0.0001057451,0.9353352,0.04025028,0.001218214,0.001957388,0.00007238877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2591878,0.0008221579,0.7319601,0.0001206243,0.00007116904,0.0001114192,0.0006073297,0.004315475,0.002803889],"genre_scores_gemma":[0.8952266,0.0003044227,0.1025975,0.00003323283,0.00001699469,0.00006429241,0.0003466108,0.0001182601,0.001292052],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009126189,"threshold_uncertainty_score":0.01814616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01754094634822565,"score_gpt":0.3095980436289964,"score_spread":0.2920570972807707,"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."}}