{"id":"W4322629835","doi":"10.1117/1.jei.32.1.013049","title":"Cascading convolutional temporal color constancy","year":2023,"lang":"en","type":"article","venue":"Journal of Electronic Imaging","topic":"Color Science and Applications","field":"Physics and Astronomy","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of British Columbia","funders":"","keywords":"Standard illuminant; Color constancy; Artificial intelligence; Computer science; Benchmark (surveying); Convolutional neural network; Chromatic adaptation; Computer vision; Pattern recognition (psychology); Deep learning; Color balance; Color image; Image (mathematics); Image processing","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":[0.0003718654,0.00006385449,0.0001113637,0.0001191581,0.0001641533,0.00004253358,0.0001566955,0.000007555966,0.0001788474],"category_scores_gemma":[0.000006270447,0.000057448,0.00009359023,0.0004076245,0.00005390806,0.0002248283,0.00002391101,0.0002025284,0.0000531171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007710435,"about_ca_system_score_gemma":0.0004573909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001732977,"about_ca_topic_score_gemma":0.000002024478,"domain_scores_codex":[0.9991763,0.00001481211,0.0002326937,0.00008335133,0.0001648177,0.0003279732],"domain_scores_gemma":[0.9995181,0.00006311911,0.0001889827,0.00006655498,0.0001069722,0.00005627246],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003319249,0.0001436544,0.3218325,0.000007556271,0.0001516912,0.00002563941,0.0005205471,0.001369702,0.03976395,0.5650952,0.04432821,0.02672805],"study_design_scores_gemma":[0.004509267,0.0003447491,0.04282477,0.0002009017,0.000215677,0.0004339051,0.006920298,0.1110555,0.01094686,0.2812513,0.5402326,0.001064124],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9728516,0.0002729252,0.01472596,0.004700861,0.0002328942,0.0001070052,0.000007199587,0.0000313881,0.007070171],"genre_scores_gemma":[0.9990845,0.000005447045,0.0001490376,0.00005597686,0.0002805432,0.00000448319,0.000003778614,0.00000568992,0.0004104856],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4959044,"threshold_uncertainty_score":0.2342662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006365471146024598,"score_gpt":0.2682865850643088,"score_spread":0.2619211139182842,"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."}}