{"id":"W2601473526","doi":"10.15353/vsnl.v2i1.103","title":"Modout: Learning to Fuse Modalities via Stochastic Regularization","year":2016,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Agence Nationale de la Recherche","keywords":"Regularization (linguistics); Modalities; Artificial intelligence; Computer science; Fuse (electrical); Dropout (neural networks); Modal; Machine learning; Equivalence (formal languages); Pattern recognition (psychology); Mathematics; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0004302046,0.00008892812,0.000153735,0.0003179882,0.0001413069,0.0002807579,0.0001414294,0.00001958204,0.000006764173],"category_scores_gemma":[0.00007112226,0.00005996014,0.00004503864,0.0001340334,0.00002100435,0.0009693207,0.00004571112,0.00007524902,0.00002359235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004442013,"about_ca_system_score_gemma":0.00004314266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003027025,"about_ca_topic_score_gemma":8.334498e-8,"domain_scores_codex":[0.9988705,0.000116104,0.0003955244,0.0001171643,0.0003928903,0.0001078428],"domain_scores_gemma":[0.9988625,0.0001909565,0.0002951017,0.00006579897,0.0004712298,0.0001143977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008802381,0.000147167,0.0006805977,0.00008799806,0.00009116611,0.00003472407,0.004337551,0.5068396,0.01355537,0.04521611,0.003781944,0.4251398],"study_design_scores_gemma":[0.001179175,0.0002582536,0.004732243,0.0008206054,0.0000138627,0.0008334474,0.0003143788,0.9576505,0.0001498442,0.03156351,0.002244386,0.0002397705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03888228,0.0001091492,0.9582725,0.002049526,0.0004906604,0.0000698715,9.448709e-7,0.00003268328,0.0000923359],"genre_scores_gemma":[0.9947444,0.000004327661,0.004513511,0.0001627967,0.0001750993,0.000001426604,0.00000108543,0.000006839904,0.0003905414],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9558621,"threshold_uncertainty_score":0.2707355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00912133655418103,"score_gpt":0.2512543076587287,"score_spread":0.2421329711045477,"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."}}