{"id":"W3109067620","doi":"10.1007/978-3-030-69532-3_21","title":"Synergistic Saliency and Depth Prediction for RGB-D Saliency Detection","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"RGB color model; Artificial intelligence; Ground truth; Computer science; Inference; Computer vision; Pattern recognition (psychology); Visualization","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008118564,0.0004942192,0.0004641482,0.0008270542,0.0005046684,0.0006540712,0.001038588,0.0003849924,0.00001247423],"category_scores_gemma":[0.0002156064,0.0004860507,0.0001671738,0.0007189256,0.0004179071,0.0007828398,0.0005639432,0.0005174613,0.00001294501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003078787,"about_ca_system_score_gemma":0.0003053987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002183834,"about_ca_topic_score_gemma":0.0002326702,"domain_scores_codex":[0.9960777,0.00005143131,0.0006354288,0.001830845,0.0008101517,0.0005944921],"domain_scores_gemma":[0.9979414,0.0003013164,0.0003039094,0.0008538566,0.0003971407,0.0002024015],"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":[0.00001123717,0.00005065454,0.00006957041,0.0001170835,0.00001493572,0.00002355025,0.0003563297,0.003235997,0.003883006,0.0234828,0.00001186346,0.968743],"study_design_scores_gemma":[0.0006875055,0.0008930459,0.001194958,0.0004628755,0.00003979251,0.0001980075,0.000001296379,0.8671861,0.01020986,0.1159174,0.002243707,0.0009654819],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000734752,0.000469037,0.992209,0.0002322847,0.004113717,0.000581989,0.00001058914,0.0002704019,0.001378288],"genre_scores_gemma":[0.8885975,0.0001672987,0.1085367,0.0006740346,0.0008197892,0.00005902556,0.00002128002,0.00005810094,0.001066186],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9677775,"threshold_uncertainty_score":0.9997591,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01886506836099714,"score_gpt":0.2589678686651208,"score_spread":0.2401028003041237,"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."}}