{"id":"W4403132043","doi":"10.1145/3698769","title":"ViCoFace: Learning Disentangled Latent Motion Representations for Visual-Consistent Face Reenactment","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Face recognition and analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Face (sociological concept); Motion (physics); Artificial intelligence; Human–computer interaction; Computer vision","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0004128482,0.000241281,0.0002720064,0.0004064653,0.001509538,0.0004770867,0.0009041398,0.00009146466,0.00001835068],"category_scores_gemma":[0.00005975466,0.0002369806,0.0002802868,0.0009537727,0.0001427504,0.0003032601,0.0001160528,0.0004013239,0.00008859323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001131083,"about_ca_system_score_gemma":0.00006245353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000354935,"about_ca_topic_score_gemma":0.00002297009,"domain_scores_codex":[0.9981204,0.0001769473,0.0005443951,0.0006468481,0.0002298412,0.0002815762],"domain_scores_gemma":[0.9961282,0.001852422,0.0001307516,0.001520317,0.0001901571,0.0001781611],"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":[0.000003654121,0.000526509,0.00009790693,0.00006216968,0.0002156813,5.958832e-7,0.001076107,0.007145838,0.001100172,0.006779016,0.00007558784,0.9829168],"study_design_scores_gemma":[0.0003433469,0.00006705093,0.0003729225,0.00008390527,0.000170433,0.0000115761,0.0005179539,0.9794429,0.0005546898,0.001424113,0.01673773,0.0002733624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007421855,0.0007734561,0.9856057,0.01073205,0.0001157531,0.001077369,0.00004582444,0.0007145003,0.0001931737],"genre_scores_gemma":[0.800151,0.001049983,0.1970454,0.0001384565,0.00004479924,0.0009529263,0.0001995135,0.00002669014,0.0003912196],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9826434,"threshold_uncertainty_score":0.9997904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03331867876417652,"score_gpt":0.3323940980028289,"score_spread":0.2990754192386523,"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."}}