{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002026542,0.0001955869,0.0002134904,0.0005266537,0.0002092488,0.0002237907,0.000610709,0.0002164052,0.000006389768],"category_scores_gemma":[0.00001886375,0.0001930526,0.0001174414,0.0006544244,0.0000727463,0.0003286534,0.00003286338,0.0003338277,0.00001990947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002202512,"about_ca_system_score_gemma":0.00007798503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001056264,"about_ca_topic_score_gemma":0.00003528356,"domain_scores_codex":[0.998462,0.00004497575,0.0003923092,0.0005987675,0.0001433624,0.0003586186],"domain_scores_gemma":[0.9992086,0.0000659352,0.00009319551,0.0004541127,0.000122603,0.00005552303],"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":[0.00004437791,0.0003765094,0.000350612,0.0009726413,0.0003013349,0.00005989148,0.0004221045,0.1223399,0.001589514,0.02273801,0.001316168,0.8494889],"study_design_scores_gemma":[0.0002378176,0.0002009694,0.000009052032,0.0005759467,0.00002949763,0.0001407882,0.0000609284,0.9909703,0.001685512,0.001450675,0.004451259,0.0001872766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004795819,0.001165413,0.9873658,0.002444686,0.002736123,0.0004318269,0.000008910137,0.00104518,0.000006200491],"genre_scores_gemma":[0.9832435,0.00004279163,0.01589718,0.0002432989,0.0000745249,0.000119476,0.00001309274,0.00002917664,0.000336999],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9784476,"threshold_uncertainty_score":0.7872456,"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."}}