{"id":"W2767290858","doi":"10.1109/msp.2017.2738401","title":"Deep Multimodal Learning: A Survey on Recent Advances and Trends","year":2017,"lang":"en","type":"article","venue":"IEEE Signal Processing Magazine","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1067,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Deep learning; Computer science; Artificial intelligence; Modalities; Multimodal learning; Field (mathematics); Machine learning; Data science","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":[0.000626336,0.0002520614,0.0002463579,0.0001634419,0.001244463,0.0008596668,0.001062092,0.00007984553,0.00002892274],"category_scores_gemma":[0.000279546,0.0002275133,0.0000366057,0.0002524838,0.0001778479,0.0007444028,0.0001878681,0.0004966368,0.0001075767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003630924,"about_ca_system_score_gemma":0.00006321509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001324254,"about_ca_topic_score_gemma":0.0001388594,"domain_scores_codex":[0.9981601,0.0001549385,0.0002519235,0.0007103377,0.0003553819,0.0003672889],"domain_scores_gemma":[0.9984518,0.0001834392,0.0003805966,0.0006169328,0.0001943262,0.0001728983],"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":[0.00003173514,0.00008369167,0.01316881,0.00002542888,0.000006593769,0.000006132066,0.000181331,0.006134303,0.0009051012,0.0001397232,0.0001005673,0.9792166],"study_design_scores_gemma":[0.0004832665,0.0001487627,0.4356905,0.0000413508,0.000005365518,0.000008241107,0.000002077804,0.5535587,0.0002460062,0.0003438167,0.009217295,0.00025461],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07983875,0.002077023,0.8894681,0.005824118,0.0003878857,0.0003202073,0.000008739545,0.000881897,0.02119322],"genre_scores_gemma":[0.9829352,0.000116251,0.01571555,0.0001337862,0.0001214128,0.00002280873,0.00001076809,0.0000254822,0.0009186745],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.978962,"threshold_uncertainty_score":0.9571533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02787362915645639,"score_gpt":0.3174627048172625,"score_spread":0.2895890756608062,"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."}}