{"id":"W4390873415","doi":"10.1109/iccv51070.2023.01202","title":"Examining Autoexposure for Challenging Scenes","year":2023,"lang":"en","type":"article","venue":"","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Canada First Research Excellence Fund","keywords":"Computer science; Shutter; Artificial intelligence; Point (geometry); Range (aeronautics); Computer vision; Software; Mathematics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007563125,0.001285755,0.0007734756,0.002180534,0.0006483658,0.001345798,0.0008996946,0.0007945434,0.003369201],"category_scores_gemma":[0.002844693,0.0003503255,0.0009581731,0.001187784,0.0004888421,0.001527153,0.001352455,0.0009335535,0.001995657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005515188,"about_ca_system_score_gemma":0.0004771008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005729869,"about_ca_topic_score_gemma":0.0243064,"domain_scores_codex":[0.999055,0.00009685849,0.00005002585,0.0003199598,0.0003032443,0.0001750068],"domain_scores_gemma":[0.9988764,0.0002759127,0.00009566768,0.000287331,0.0003902156,0.00007456898],"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":[0.00130529,0.0007120916,0.03884705,0.00405201,0.0006486881,0.001166735,0.000893692,0.02514541,0.1007482,0.003294522,0.1671156,0.6560706],"study_design_scores_gemma":[0.0002157283,0.00134152,0.2626573,0.001143481,0.0004802615,0.009115088,0.003118716,0.2223783,0.1750506,0.01128585,0.3128562,0.0003569651],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6225294,0.01236619,0.2014448,0.001476938,0.001807051,0.001395662,0.09167525,0.02928149,0.0380232],"genre_scores_gemma":[0.6231645,0.003749624,0.2256655,0.0009233169,0.0003906275,0.0003545136,0.1340721,0.003030687,0.008649157],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005729869,"threshold_uncertainty_score":0.01139301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0798597046753562,"score_gpt":0.2984972285027806,"score_spread":0.2186375238274244,"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."}}