{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004781387,0.0011247,0.0007140314,0.0006743255,0.0002715952,0.0005405837,0.001622373,0.0007050518,0.002011775],"category_scores_gemma":[0.001388826,0.0004091825,0.0006996168,0.0004554774,0.0003538262,0.001103059,0.001040195,0.0007290554,0.0004853961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008381771,"about_ca_system_score_gemma":0.0005225816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005419109,"about_ca_topic_score_gemma":0.008008656,"domain_scores_codex":[0.9997405,0.00003833359,0.00001037915,0.00008958385,0.00006787405,0.00005321539],"domain_scores_gemma":[0.9997472,0.00007725078,0.00003628642,0.00003005348,0.00008204549,0.00002721582],"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":[0.000450236,0.0001900206,0.00265764,0.0002816062,0.0002576747,0.0003058458,0.0001972022,0.3011115,0.09032935,0.008096883,0.007810253,0.5883119],"study_design_scores_gemma":[0.000009732475,0.00005513181,0.0005234613,0.00000802866,0.00002772741,0.00006759414,0.00001062975,0.9890518,0.007072347,0.002111759,0.001049663,0.00001213541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02925809,0.001030284,0.9647329,0.000196475,0.0001155647,0.00007619207,0.0001551449,0.001744055,0.002691312],"genre_scores_gemma":[0.78745,0.0006560546,0.2048869,0.000400014,0.0001288943,0.0001447654,0.0005108496,0.0001902212,0.005632396],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005419109,"threshold_uncertainty_score":0.01077515,"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."}}