{"id":"W2272596542","doi":"10.1007/s00371-015-1184-x","title":"Mesh saliency detection via double absorbing Markov chain in feature space","year":2015,"lang":"en","type":"article","venue":"The Visual Computer","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Markov chain; Computer science; Laplacian smoothing; Blob detection; Feature (linguistics); Laplace operator; Artificial intelligence; Pattern recognition (psychology); Absorbing Markov chain; Salient; Partition (number theory); Algorithm; Smoothing; Feature vector; Computer vision; Mathematics; Image (mathematics); Markov model; Edge detection; Image processing; Variable-order Markov model; Combinatorics; Mesh generation","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":[0.0009976715,0.0002067465,0.0001885704,0.0002336047,0.0001805315,0.0002261605,0.0006674243,0.0001137332,0.000007155983],"category_scores_gemma":[0.00001053937,0.0001536362,0.00008789269,0.001001089,0.00005619809,0.000540352,0.0003492992,0.0003529702,0.0001717611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001329442,"about_ca_system_score_gemma":0.00004025642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001696805,"about_ca_topic_score_gemma":0.0001289926,"domain_scores_codex":[0.9982288,0.0002392246,0.0002503735,0.0004499369,0.0004467328,0.0003848679],"domain_scores_gemma":[0.9991844,0.00004606476,0.0001102982,0.0004214501,0.0001043193,0.0001334642],"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":[0.0006855964,0.001270971,0.00326703,0.00009876256,0.0001142268,0.0001475216,0.02137096,0.004901267,0.02154941,0.04800243,0.009849673,0.8887421],"study_design_scores_gemma":[0.002002876,0.0007249422,0.009247866,0.00004819224,0.000008151854,0.0001354803,0.0001673262,0.9710056,0.00910977,0.002736988,0.004346968,0.0004658155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2387977,0.00007241764,0.7563176,0.001573218,0.001865292,0.0002804645,2.293132e-7,0.0002853108,0.0008077825],"genre_scores_gemma":[0.9948984,0.000004335545,0.003613307,0.0005004372,0.0003421599,0.00002112849,0.000001662454,0.00001534202,0.0006032486],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9661043,"threshold_uncertainty_score":0.6265102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02308774106452338,"score_gpt":0.2819964231903871,"score_spread":0.2589086821258637,"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."}}