{"id":"W4226136518","doi":"10.1049/cit2.12090","title":"A weighted block cooperative sparse representation algorithm based on visual saliency dictionary","year":2022,"lang":"en","type":"article","venue":"CAAI Transactions on Intelligence Technology","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Sparse approximation; Neural coding; Pattern recognition (psychology); Salient; Computer science; Artificial intelligence; Block (permutation group theory); Coding (social sciences); K-SVD; Representation (politics); Residual; Algorithm; Mathematics","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":[0.0002314113,0.0002538043,0.0002211884,0.001411773,0.001206178,0.00006173712,0.0007419248,0.0001552761,0.0005983988],"category_scores_gemma":[0.00002270557,0.0002691017,0.0001463041,0.003477579,0.0001845995,0.0002749994,0.00003465783,0.0008330073,0.0002127255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000317485,"about_ca_system_score_gemma":0.0001257923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002489557,"about_ca_topic_score_gemma":0.000006543686,"domain_scores_codex":[0.9975292,0.0002377179,0.0004491504,0.000853672,0.0005681798,0.0003620686],"domain_scores_gemma":[0.998827,0.0001218413,0.0001361438,0.0006471309,0.0001782406,0.00008961152],"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":[0.0001364685,0.002643008,0.00005818316,0.000008034738,0.0000641602,0.00009410369,0.0005068624,0.1606046,0.002760506,0.02332107,0.000280467,0.8095226],"study_design_scores_gemma":[0.0002911676,0.002813503,0.00006490856,0.00001546458,0.00001636714,0.0001318634,0.0008958586,0.9313676,0.05743746,0.004566202,0.002064906,0.0003346751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006899463,0.00002294939,0.9866611,0.002881545,0.001310491,0.0004529981,0.00002506259,0.001132712,0.0006136526],"genre_scores_gemma":[0.9893971,0.00002426752,0.008529569,0.0006633584,0.00002489626,0.0006552014,0.00001332668,0.00002127329,0.0006710058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9824976,"threshold_uncertainty_score":0.9999761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02023162553009298,"score_gpt":0.2976008848444051,"score_spread":0.2773692593143121,"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."}}