{"id":"W4393156087","doi":"10.1609/aaai.v38i4.28151","title":"Test-Time Personalization with Meta Prompt for Gaze Estimation","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; University of Toronto; University of Waterloo","funders":"","keywords":"Personalization; Gaze; Test (biology); Estimation; Meta-analysis; Computer science; Psychology; Artificial intelligence; Medicine; Engineering; World Wide Web; Geology","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":[0.001981583,0.001660033,0.0008426379,0.0007924961,0.0003280515,0.0006197078,0.001305246,0.001159605,0.003035323],"category_scores_gemma":[0.01274854,0.000389046,0.0005299192,0.0004322895,0.0003131859,0.001822302,0.001274783,0.001620402,0.001408235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004759067,"about_ca_system_score_gemma":0.0005757753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00339616,"about_ca_topic_score_gemma":0.005666006,"domain_scores_codex":[0.9986105,0.0004335668,0.0000730562,0.0005459561,0.0002186286,0.0001181951],"domain_scores_gemma":[0.9961528,0.001320518,0.0002065161,0.001401412,0.0007501437,0.0001686042],"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":[0.001539649,0.001003051,0.02041951,0.0003869975,0.0003272209,0.0003115264,0.0004357387,0.1184473,0.06946706,0.0008658727,0.01754218,0.7692538],"study_design_scores_gemma":[0.0001358469,0.0006616218,0.01449544,0.00004026296,0.00007582062,0.0002420662,0.0001743308,0.93651,0.04149789,0.002824461,0.00328524,0.00005698184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3604545,0.001255515,0.5833787,0.0004245095,0.000468525,0.0003481196,0.001779552,0.0481851,0.003705417],"genre_scores_gemma":[0.8621665,0.0001392584,0.1311617,0.0002029639,0.00008287072,0.0003026492,0.002274628,0.0008022957,0.002867247],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00339616,"threshold_uncertainty_score":0.01047975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07552402674694116,"score_gpt":0.2975394259052834,"score_spread":0.2220153991583422,"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."}}