{"id":"W4413277779","doi":"10.1109/taffc.2025.3599859","title":"Leveraging Eye Movement for Instructing Robust Video-Based Facial Expression Recognition","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Affective Computing","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Hubei Key Laboratory of Intelligent Geo-Information Processing; Natural Science Foundation of Hubei Province; National Natural Science Foundation of China","keywords":"Facial expression; Computer science; Facial expression recognition; Computer vision; Eye movement; Artificial intelligence; Emotion recognition; Expression (computer science); Speech recognition; Human–computer interaction; Facial recognition system; Feature extraction","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":[0.0006445899,0.001020716,0.0006509502,0.0005288281,0.0001996233,0.0004092274,0.001021159,0.0005220691,0.002413563],"category_scores_gemma":[0.002362146,0.0002760723,0.0006780389,0.0002941178,0.0002483733,0.0007684255,0.0006485645,0.001050338,0.001522229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004289142,"about_ca_system_score_gemma":0.0003534061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004700384,"about_ca_topic_score_gemma":0.009439459,"domain_scores_codex":[0.9994997,0.00009120652,0.00001831547,0.000247632,0.0000796082,0.00006348868],"domain_scores_gemma":[0.9996414,0.000122574,0.00003070316,0.0000911618,0.00009573565,0.00001839285],"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":[0.0004739226,0.0002914136,0.006536078,0.0002522966,0.0001449293,0.0001340657,0.0001271345,0.03512566,0.1665032,0.001092754,0.01624216,0.7730764],"study_design_scores_gemma":[0.00005088995,0.0002298126,0.009695702,0.00003537083,0.00007481009,0.0002141959,0.00006958486,0.894659,0.0868445,0.001787698,0.006297765,0.00004069934],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2298372,0.002362356,0.734767,0.0005301682,0.0004006435,0.0004110216,0.00320473,0.01954369,0.008943289],"genre_scores_gemma":[0.7044804,0.000799013,0.2760865,0.0005556401,0.0001070483,0.0003728229,0.007290004,0.0007356642,0.009572944],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004700384,"threshold_uncertainty_score":0.009346068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02881493789973664,"score_gpt":0.2737631537182268,"score_spread":0.2449482158184902,"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."}}