{"id":"W4226025707","doi":"10.1016/j.inffus.2022.03.001","title":"Multimodal Attentive Fusion Network for audio-visual event recognition","year":2022,"lang":"en","type":"article","venue":"Information Fusion","topic":"Music and Audio Processing","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"European Regional Development Fund; Fonds de recherche du Québec – Nature et technologies; Nvidia","keywords":"Computer science; Audio visual; Event (particle physics); Modality (human–computer interaction); Window (computing); Fuse (electrical); Modalities; Artificial intelligence; Focus (optics); Multimodality; Code (set theory); Visualization; Speech recognition; Set (abstract data type); Multimedia","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":[0.0005771155,0.000111331,0.0001089261,0.0001209239,0.001080098,0.0001498864,0.0002882207,0.00004082432,0.0001710332],"category_scores_gemma":[0.00003745835,0.0001104935,0.00008066054,0.0003734647,0.0000127836,0.001823778,0.0004463568,0.0001345328,0.0000861326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001109592,"about_ca_system_score_gemma":0.00007455354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001349731,"about_ca_topic_score_gemma":0.000001466114,"domain_scores_codex":[0.9987624,0.00005448329,0.0003695736,0.0001620051,0.000401768,0.0002498007],"domain_scores_gemma":[0.999261,0.00005972662,0.0003120353,0.0001485483,0.0001634956,0.00005515424],"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":[0.00005884145,0.00004985565,0.00008754434,0.00003682245,0.000006360825,6.999628e-7,0.00233055,0.008969328,0.0004607215,0.000571523,0.01953397,0.9678938],"study_design_scores_gemma":[0.00125683,0.0002890958,0.001990593,0.00005602292,0.000009751569,0.00001843083,0.0003896022,0.8026491,0.0008226584,0.0025527,0.1896534,0.0003117864],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07697205,0.00002714089,0.9186901,0.0009306715,0.00127889,0.0006255957,0.00002050983,0.0001796027,0.001275462],"genre_scores_gemma":[0.9439054,0.00001381551,0.04969726,0.004631879,0.0003304447,0.0005304946,0.0006553304,0.00001025662,0.0002251882],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.967582,"threshold_uncertainty_score":0.8307347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01670245718060828,"score_gpt":0.2551667884741185,"score_spread":0.2384643312935102,"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."}}