{"id":"W2799228606","doi":"10.1109/cvpr.2018.00674","title":"Improving Color Reproduction Accuracy on Cameras","year":2018,"lang":"en","type":"article","venue":"","topic":"Color Science and Applications","field":"Physics and Astronomy","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer vision; Color balance; Artificial intelligence; Color space; Computer science; Interpolation (computer graphics); Color correction; False color; Color histogram; Process (computing); Demosaicing; ICC profile; Color image; Computer graphics (images); Color model; Image processing; Image (mathematics)","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007038253,0.00004208549,0.00003638896,0.00001837593,0.0001831659,0.0000345,0.00008134469,0.000007468705,0.00100098],"category_scores_gemma":[0.000010022,0.00003418547,0.00002086188,0.0001419256,0.00004680626,0.0001036322,0.00002224963,0.00003690535,0.000720069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008267149,"about_ca_system_score_gemma":0.00002469869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003486716,"about_ca_topic_score_gemma":0.000008570679,"domain_scores_codex":[0.999563,0.000004475895,0.00006652408,0.0002090203,0.00005588201,0.0001010635],"domain_scores_gemma":[0.9996281,0.00002075099,0.00003603237,0.0002413583,0.00004566197,0.00002814892],"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":[0.00001190231,0.0001682326,0.005417944,0.000001244525,0.000009505605,8.061819e-8,0.0002679628,0.00001894813,0.06324261,0.246747,0.01587436,0.6682402],"study_design_scores_gemma":[0.0004873336,0.0004955806,0.01649887,0.000009558476,0.00002245258,0.000001091562,0.001552391,0.008775306,0.588739,0.01372834,0.3692333,0.0004568112],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8996969,9.953123e-7,0.007541192,0.001267001,0.0001395185,0.0001400978,0.000002030769,0.00004183049,0.0911704],"genre_scores_gemma":[0.9949811,1.102072e-7,0.000638928,0.0001305329,0.0007596022,0.00003238523,0.000002802253,0.000002870239,0.003451693],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6677834,"threshold_uncertainty_score":0.9999123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01433688742309941,"score_gpt":0.2890755391427922,"score_spread":0.2747386517196928,"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."}}