{"id":"W4400335279","doi":"10.1007/s11042-024-19365-8","title":"SFI-Swin: symmetric face inpainting with swin transformer by distinctly learning face components distributions","year":2024,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Inpainting; Transformer; Face (sociological concept); Artificial intelligence; Computer vision; Pattern recognition (psychology); Image (mathematics); Electrical 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":[0.0001885117,0.0001993872,0.0001829395,0.00007814453,0.0005303292,0.0006054659,0.0003028054,0.00006091917,0.0000202018],"category_scores_gemma":[0.00004016054,0.0001610149,0.00005722721,0.0008916889,0.0001014833,0.0005157314,0.00006536184,0.0002652756,0.00005706312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003708432,"about_ca_system_score_gemma":0.00003436066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005080495,"about_ca_topic_score_gemma":0.000006333146,"domain_scores_codex":[0.9986769,0.00005750942,0.0002304492,0.0005168726,0.0001996543,0.0003185987],"domain_scores_gemma":[0.999081,0.0004243268,0.0000525637,0.0002318938,0.00005796301,0.0001522953],"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":[0.00000565283,0.000164291,0.001166999,0.00006395863,0.0001139233,0.000006017519,0.001020379,0.002744842,0.01770568,0.008017237,0.002397112,0.9665939],"study_design_scores_gemma":[0.0003296258,0.00005770435,0.00327122,0.00006684564,0.00004603642,0.00001660779,0.0002051221,0.786716,0.003204193,0.000144281,0.2055394,0.0004030135],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00349563,0.0009317057,0.992117,0.001567389,0.00006105734,0.0005033175,0.0001651074,0.0001993133,0.0009595092],"genre_scores_gemma":[0.9756012,0.0001220164,0.02298114,0.00004674855,0.0001182023,0.0003009762,0.0002565615,0.00001651164,0.0005566381],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9721056,"threshold_uncertainty_score":0.6565995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01471046436595284,"score_gpt":0.2299891709001861,"score_spread":0.2152787065342333,"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."}}