{"id":"W4405627619","doi":"10.1109/iccv51701.2025.01349","title":"SEREP: Semantic Facial Expression Representation for Robust in-the-Wild Capture and Retargeting","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Retargeting; Representation (politics); Computer science; Expression (computer science); Facial expression; Artificial intelligence; Natural language processing; Computational biology; Computer vision; Biology; Programming language; Political science","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":[0.000811775,0.001209496,0.0007477422,0.0004771115,0.0002293993,0.0006888936,0.00153305,0.0007426019,0.002489287],"category_scores_gemma":[0.001850197,0.0003958569,0.0007236921,0.0003900219,0.000539637,0.001164429,0.001853563,0.00123402,0.002150785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004288293,"about_ca_system_score_gemma":0.0006389094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003016218,"about_ca_topic_score_gemma":0.004290915,"domain_scores_codex":[0.9993118,0.000127761,0.00001948908,0.0002300472,0.0002160257,0.00009482683],"domain_scores_gemma":[0.9995725,0.00008214459,0.00003636078,0.0001816017,0.00009978103,0.00002771022],"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":[0.0005194956,0.00028795,0.001877242,0.0002410337,0.0001656828,0.0002745825,0.00022966,0.1161641,0.1689416,0.00585916,0.02535261,0.6800869],"study_design_scores_gemma":[0.00002170118,0.000161357,0.001871482,0.0000251426,0.00003788032,0.0004088808,0.00008098162,0.9311369,0.05365745,0.005138451,0.007421012,0.00003865645],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0352475,0.00040404,0.9527259,0.0001655558,0.0001238325,0.0001352439,0.0009764446,0.007470104,0.002751369],"genre_scores_gemma":[0.4804062,0.0007774878,0.4980582,0.0005014359,0.00009095671,0.0004896976,0.00700024,0.001504071,0.0111718],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003016218,"threshold_uncertainty_score":0.008327544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03870746230977511,"score_gpt":0.2912098910720005,"score_spread":0.2525024287622254,"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."}}