{"id":"W4399526356","doi":"10.1109/tcsvt.2024.3412243","title":"TTAGaze: Self-Supervised Test-Time Adaptation for Personalized Gaze Estimation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China","keywords":"Computer science; Gaze; Adaptation (eye); Artificial intelligence; Test (biology); Computer vision; Estimation; Machine learning; Psychology; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003807607,0.0002556132,0.0003603702,0.0008107053,0.0003575382,0.0002367172,0.0003821883,0.0003548852,0.000003451178],"category_scores_gemma":[0.00006002005,0.0002422241,0.0001415465,0.0006515838,0.0001222721,0.0003254432,0.000003248217,0.000245797,0.00003441153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001118782,"about_ca_system_score_gemma":0.000105698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001131998,"about_ca_topic_score_gemma":0.000004986718,"domain_scores_codex":[0.9983009,0.00003291294,0.0003966438,0.0007194278,0.0001676933,0.0003824995],"domain_scores_gemma":[0.9985039,0.0007640572,0.00008644235,0.0004036899,0.0001795926,0.00006234417],"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":[0.00002292127,0.0002766439,0.000007240133,0.0008733161,0.0002300081,0.00001574053,0.0008952305,0.003299135,0.0219164,0.1338445,0.001299741,0.8373191],"study_design_scores_gemma":[0.0007884983,0.0006741669,0.000007383983,0.0002151738,0.00008205955,0.0001649992,0.0001305237,0.9802125,0.006620936,0.003462949,0.007358233,0.0002825899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004647422,0.0007137625,0.98682,0.002135566,0.001237281,0.001183952,0.0001038269,0.003113891,0.00004433764],"genre_scores_gemma":[0.9835782,0.00004804089,0.01396488,0.00006049842,0.00003689856,0.001229274,0.000006386203,0.00003746624,0.001038372],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9789308,"threshold_uncertainty_score":0.9877613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02321060151935446,"score_gpt":0.2569139773032614,"score_spread":0.233703375783907,"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."}}