{"id":"W4214831601","doi":"10.1109/tip.2022.3154931","title":"DMRA: Depth-Induced Multi-Scale Recurrent Attention Network for RGB-D Saliency Detection","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Natural Science Foundation of Liaoning Province; National Natural Science Foundation of China; University of Alberta","keywords":"Computer science; RGB color model; Artificial intelligence; Benchmark (surveying); Pattern recognition (psychology); Feature (linguistics); Fuse (electrical); Block (permutation group theory); Scale (ratio); Salient; Computer vision","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00055227,0.0002470352,0.000205608,0.0002888206,0.002565472,0.0003066634,0.0004364866,0.00007515845,0.00003285627],"category_scores_gemma":[0.00000774769,0.0002738609,0.0002509787,0.001165253,0.0000347716,0.001057769,0.00001044332,0.0004685186,0.00002750466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002834992,"about_ca_system_score_gemma":0.00008653713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002122817,"about_ca_topic_score_gemma":0.0001299327,"domain_scores_codex":[0.9976748,0.000181431,0.0004600419,0.000725818,0.0004718493,0.0004860804],"domain_scores_gemma":[0.9990836,0.00004508517,0.0002321735,0.0003284175,0.000196375,0.0001143595],"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":[0.00009481777,0.0006385278,0.00001209279,0.00007480418,0.00001773508,0.00000209386,0.0004927742,0.006097253,0.1411702,0.00001936799,0.00006240563,0.8513179],"study_design_scores_gemma":[0.001633364,0.001037885,0.0007059603,0.0000667006,0.00006201598,0.00007948806,0.0003849368,0.9163132,0.07772307,0.0004718655,0.0009493399,0.000572214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02038038,0.0000636924,0.9747795,0.0002418039,0.003236778,0.0006094605,0.00001145488,0.0005788894,0.00009798729],"genre_scores_gemma":[0.9505371,0.000007708209,0.04799576,0.0001719958,0.0001122689,0.0007806912,0.000005684792,0.00003440754,0.0003543447],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9301568,"threshold_uncertainty_score":0.9999713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03690044911600793,"score_gpt":0.3064469650894981,"score_spread":0.2695465159734902,"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."}}