{"id":"W2963853153","doi":"","title":"Recurrent Mixture Density Network for Spatiotemporal Visual Attention","year":2016,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Artificial intelligence; Weighting; Visual attention; Consistency (knowledge bases); Focus (optics); Salient; Frame (networking); Pattern recognition (psychology); Fixation (population genetics); Pixel; Computer vision; Cognition","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":[0.0002229705,0.0001212867,0.0001159073,0.00007934456,0.000230998,0.00004129052,0.0003148279,0.00008625568,0.0000164096],"category_scores_gemma":[0.0000246618,0.0001022814,0.0001450011,0.0004217535,0.00004036049,0.000563697,0.0001071576,0.00006119756,0.00008953975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009744793,"about_ca_system_score_gemma":0.00002906861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001171852,"about_ca_topic_score_gemma":0.00005969216,"domain_scores_codex":[0.9989699,0.00008339679,0.0001273108,0.0004875183,0.00006793442,0.0002639617],"domain_scores_gemma":[0.999323,0.00005360623,0.0001139138,0.0002617762,0.000145601,0.0001021374],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004433545,0.0005381011,0.0778692,0.00006225476,0.0001276043,0.00007282934,0.0001483353,0.001684005,0.007280713,0.7834394,0.01020771,0.1181265],"study_design_scores_gemma":[0.005267583,0.001838066,0.1657848,0.0002313551,0.0001121574,0.00002684264,0.00007272024,0.6921821,0.003621667,0.1115016,0.01796929,0.001391808],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3700383,0.000005364255,0.6288261,0.0001943176,0.0005970091,0.000129489,0.000001814393,0.0001239241,0.00008369025],"genre_scores_gemma":[0.9967965,0.00001651702,0.001170889,0.00007905885,0.0001385472,9.686078e-7,0.000004482284,0.000006473449,0.001786488],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6904981,"threshold_uncertainty_score":0.4170913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04908631685809894,"score_gpt":0.2091797688879366,"score_spread":0.1600934520298377,"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."}}