{"id":"W4311972917","doi":"10.1007/s11263-022-01734-1","title":"Delving into Calibrated Depth for Accurate RGB-D Salient Object Detection","year":2022,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; RGB color model; Computer vision; Boosting (machine learning); Salient; Pixel; Boundary (topology); Depth map; Pattern recognition (psychology); Image (mathematics); Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007654519,0.0001325107,0.0001696675,0.0005185235,0.0003011418,0.0003354106,0.001136717,0.00003656395,0.00002632861],"category_scores_gemma":[0.0000364208,0.0001234374,0.000232689,0.000335235,0.00001659987,0.001010618,0.0004623506,0.0002476248,0.000006163027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003033387,"about_ca_system_score_gemma":0.00009077668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001943459,"about_ca_topic_score_gemma":0.00001038118,"domain_scores_codex":[0.9978792,0.0001907671,0.0006253082,0.0002494328,0.0008903745,0.0001649118],"domain_scores_gemma":[0.9983991,0.0001176141,0.0005692443,0.0001556228,0.0006692804,0.00008916596],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004588718,0.000545782,0.0003727096,0.00001532107,0.0002364128,0.0001301962,0.001496628,0.06403141,0.04555882,0.004065411,0.003630558,0.8794579],"study_design_scores_gemma":[0.001594628,0.00214473,0.003817,0.00004592528,0.00001278971,0.0006414757,0.00006575073,0.9553255,0.01135194,0.005996968,0.01877862,0.0002246926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1430326,0.00004242849,0.8485152,0.001023636,0.007167432,0.000122966,0.000001749304,0.00005926111,0.00003473436],"genre_scores_gemma":[0.972832,0.00000956234,0.02588544,0.0007233921,0.0004821992,0.00001185604,0.000004996558,0.00001214216,0.0000384386],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8912941,"threshold_uncertainty_score":0.5033633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01666215506869933,"score_gpt":0.3194970083776447,"score_spread":0.3028348533089453,"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."}}