{"id":"W2154071538","doi":"10.1162/neco_a_00312","title":"Learning Where to Attend with Deep Architectures for Image Tracking","year":2012,"lang":"en","type":"article","venue":"Neural Computation","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":200,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Eye tracking; Computer vision; Gaze; Orientation (vector space); Reinforcement learning; Object (grammar); Fixation (population genetics); Boltzmann machine; Action selection; Machine learning; Perception; Deep learning; Mathematics; Psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.0001467459,0.00009825613,0.00008688288,0.0001017625,0.0002130503,0.0001471537,0.0001320767,0.00002452469,0.000003412707],"category_scores_gemma":[0.00002745388,0.00008177834,0.00004164267,0.0002502337,0.00001147964,0.0002904932,0.00003402052,0.0001056973,0.00002184067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002312424,"about_ca_system_score_gemma":0.000005844907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006869047,"about_ca_topic_score_gemma":0.00001724308,"domain_scores_codex":[0.9991821,0.00006545427,0.0001281284,0.0002035522,0.0001757001,0.0002450675],"domain_scores_gemma":[0.9996031,0.00006678146,0.00006533799,0.00007749148,0.00009401717,0.00009326064],"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":[0.0000728651,0.00008741631,0.005629856,0.00005630432,0.00001583057,0.000003026067,0.005663114,0.1712954,0.01614183,0.0007809813,0.000226469,0.800027],"study_design_scores_gemma":[0.0004892896,0.0008680043,0.06779978,0.00002205055,0.000009430519,0.00007194845,0.0001470661,0.9258743,0.003476464,0.0004280603,0.0005565024,0.0002571442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4228337,0.00001306153,0.5762571,0.0003593123,0.0001686473,0.0001509641,2.288323e-7,0.0001303287,0.00008666896],"genre_scores_gemma":[0.9517406,1.897107e-7,0.04782287,0.0002355194,0.0001216602,0.00001987135,0.000003550532,0.00001031149,0.00004542718],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7997698,"threshold_uncertainty_score":0.3334824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02223441900648307,"score_gpt":0.3043333604364766,"score_spread":0.2820989414299936,"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."}}