{"id":"W197365134","doi":"10.1007/978-3-642-31295-3_10","title":"Biologically Motivated Local Contextual Modulation Improves Low-Level Visual Feature Representations","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Artificial intelligence; Computation; Feature (linguistics); Computer science; Context (archaeology); Representation (politics); Pattern recognition (psychology); Modulation (music); Computer vision; Pixel; Human visual system model; Variety (cybernetics); Image (mathematics); Algorithm; Geography","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":[0.0006825855,0.0005373323,0.0004745265,0.0007306735,0.00040964,0.0004530643,0.001582463,0.0005866299,0.00004168727],"category_scores_gemma":[0.0001610361,0.0004532036,0.0001938711,0.0008075293,0.0007842184,0.001057129,0.0008391264,0.0008932825,0.0001113012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003009654,"about_ca_system_score_gemma":0.0002418835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003359411,"about_ca_topic_score_gemma":0.00004676456,"domain_scores_codex":[0.9962304,0.00008967207,0.0005733241,0.001494819,0.0009159904,0.0006957424],"domain_scores_gemma":[0.9978234,0.0003198379,0.0003549274,0.0008279058,0.0004319173,0.0002420107],"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":[0.00001486919,0.00009349758,0.0001366059,0.00002080163,0.00001693809,0.00001670349,0.0004126829,0.008758279,0.005460553,0.01062804,0.00003287012,0.9744081],"study_design_scores_gemma":[0.0005443685,0.0004111221,0.0143346,0.0001995602,0.00001318565,0.00008605039,0.000001648536,0.9381431,0.003789281,0.04107929,0.0004658085,0.0009319258],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002043982,0.0001424798,0.9935521,0.0006784147,0.002027897,0.0004767604,0.000009372206,0.0003109781,0.0007580562],"genre_scores_gemma":[0.93998,0.00002219221,0.05783555,0.0009666866,0.0004725044,0.000014784,0.00003627447,0.00002679417,0.0006452216],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9734762,"threshold_uncertainty_score":0.999792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03076143432868427,"score_gpt":0.2900228388363633,"score_spread":0.259261404507679,"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."}}