{"id":"W4392908102","doi":"10.1109/tcsvt.2024.3377108","title":"Low-Light Salient Object Detection by Learning to Highlight the Foreground Objects","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Science Foundation of Hainan Province; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Computer vision; Salient; Object detection; Object (grammar); Pattern recognition (psychology)","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":[0.0004537871,0.0002348633,0.0002417648,0.0006610035,0.0008129201,0.0004760269,0.0003699427,0.0002194949,0.000003705094],"category_scores_gemma":[0.00001509781,0.0001735819,0.0001324266,0.001092512,0.0000572009,0.0003044997,0.000006183418,0.0003947707,0.00007005475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001472837,"about_ca_system_score_gemma":0.00003355811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005264422,"about_ca_topic_score_gemma":0.00009206666,"domain_scores_codex":[0.9981883,0.0000930822,0.0003730363,0.0006920319,0.0002593044,0.0003942066],"domain_scores_gemma":[0.9991916,0.0001523037,0.00006944795,0.0003900534,0.0001014271,0.00009512616],"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":[0.00002936511,0.0002013379,0.000006345314,0.0004313611,0.0002378987,0.00001737464,0.002157991,0.002949097,0.3114471,0.02459808,0.001736972,0.656187],"study_design_scores_gemma":[0.001004042,0.00377969,0.00002950321,0.0005048006,0.0001249226,0.000624698,0.002036411,0.2184692,0.5692495,0.002911513,0.2002561,0.00100975],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03663266,0.0007101709,0.9545958,0.001986337,0.003812531,0.0009272445,0.00001110039,0.001192873,0.0001312786],"genre_scores_gemma":[0.9978183,0.00005681408,0.00003566886,0.0001530894,0.00006103779,0.0006941679,8.923793e-7,0.00002840983,0.001151649],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9611856,"threshold_uncertainty_score":0.7078462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01276119692287182,"score_gpt":0.250924327656261,"score_spread":0.2381631307333892,"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."}}