{"id":"W4392885584","doi":"10.1145/3653018","title":"Audio-Visual Event Localization using Multi-task Hybrid Attention Networks for Smart Healthcare Systems","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Internet Technology","topic":"Music and Audio Processing","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University","funders":"Humanities and Social Science Fund of Ministry of Education of China; Fundamental Research Funds for the Central Universities; Central China Normal University; China Scholarship Council; Ministry of Education of the People's Republic of China; National Natural Science Foundation of China","keywords":"Computer science; Task (project management); Event (particle physics); Modal; Representation (politics); Block (permutation group theory); Artificial intelligence; Human–computer interaction; Perception; Feature learning; Multi-task learning; Multimodal learning; Semantics (computer science); Machine learning; Deep learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00106417,0.00134965,0.0009617287,0.0008733661,0.0003677601,0.0007689646,0.001601583,0.001217056,0.002019446],"category_scores_gemma":[0.00213823,0.000402017,0.0008929197,0.0007665663,0.0004047528,0.001341145,0.001449708,0.001467248,0.0004688954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001050138,"about_ca_system_score_gemma":0.0007603699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0123094,"about_ca_topic_score_gemma":0.009888577,"domain_scores_codex":[0.9995176,0.0001236212,0.00002331934,0.0001669814,0.00007571588,0.00009286871],"domain_scores_gemma":[0.9994376,0.0003088229,0.00004909156,0.00003314603,0.0001381371,0.00003315959],"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":[0.0006050821,0.0003375954,0.00231279,0.0002453309,0.0002292767,0.0002760089,0.0001874561,0.6058661,0.0138705,0.003162777,0.005597723,0.3673094],"study_design_scores_gemma":[0.000006113135,0.00003535558,0.0003085623,0.000005801051,0.00002245752,0.00001992747,0.00001235834,0.9965355,0.0008936417,0.001756477,0.0003974696,0.000006266507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06315453,0.005494936,0.9234288,0.001088032,0.0003159609,0.0001112125,0.0003077303,0.002253667,0.003845156],"genre_scores_gemma":[0.9347143,0.001211229,0.05739124,0.0006396877,0.0003215527,0.0001594222,0.0005810082,0.0001080724,0.004873445],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0123094,"threshold_uncertainty_score":0.02447551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02951260293481954,"score_gpt":0.3121271462095536,"score_spread":0.2826145432747341,"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."}}