{"id":"W4385333918","doi":"10.1109/isscs58449.2023.10190977","title":"Counterfactual Attention for Facial Image Super-Resolution","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Counterfactual thinking; Task (project management); Computer science; Integer (computer science); Artificial intelligence; Scale (ratio); Inference; Quality (philosophy); Image quality; Face (sociological concept); Field (mathematics); Image (mathematics); Resolution (logic); Machine learning; Computer vision; Pattern recognition (psychology); Mathematics; Psychology; Engineering; Geography","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":[0.0002035887,0.0000863602,0.00007857705,0.0001073944,0.0001512728,0.000162138,0.0004096048,0.00003884048,0.000008126415],"category_scores_gemma":[0.00008360494,0.00008106174,0.00004523055,0.0003018168,0.00003903223,0.001206975,0.0001667919,0.00004931703,0.0001437674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004183941,"about_ca_system_score_gemma":0.00002859625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005496822,"about_ca_topic_score_gemma":0.000002709344,"domain_scores_codex":[0.9991701,0.00001162383,0.0001337328,0.0002808732,0.0001561013,0.0002475203],"domain_scores_gemma":[0.9995292,0.00004520099,0.00003499789,0.0002317543,0.0001268268,0.00003202862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002944332,0.00007789781,0.0001717354,0.00008716665,0.00001413527,0.000009195852,0.0005688666,0.00002456807,0.6647059,0.04145982,0.09203433,0.200817],"study_design_scores_gemma":[0.0004573424,0.0001554343,0.001089918,0.00002348694,0.000004826792,0.000009011826,0.00005368937,0.8580995,0.05122244,0.06269316,0.02586139,0.000329758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002746416,0.000008895681,0.9927512,0.001038645,0.0001843288,0.0001955414,0.000005909983,0.002359565,0.0007095175],"genre_scores_gemma":[0.1135793,0.000006512205,0.8842625,0.0001643729,0.00006494996,0.00008299962,0.00001874954,0.0000117816,0.001808788],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.858075,"threshold_uncertainty_score":0.3305602,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02625751562334962,"score_gpt":0.3148814894898669,"score_spread":0.2886239738665173,"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."}}