{"id":"W4390412297","doi":"10.18280/ts.400647","title":"Enhancing Drowning Surveillance with a Hybrid Vision Transformer Model: A Deep Learning Approach","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Education of the People's Republic of China","keywords":"Transformer; Artificial intelligence; Computer science; Deep learning; Computer vision; Machine learning; Real-time computing; Computer security; Engineering; Electrical engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002499674,0.0007056392,0.0004950869,0.0004889744,0.0001357836,0.0005283439,0.0008792174,0.0005452358,0.000890441],"category_scores_gemma":[0.0005439558,0.0002509826,0.0005402495,0.0003528163,0.0002196966,0.0006673211,0.0005843031,0.0007966073,0.0003928044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006068187,"about_ca_system_score_gemma":0.0005977366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01036159,"about_ca_topic_score_gemma":0.01200443,"domain_scores_codex":[0.9999043,0.00001309794,0.000003915888,0.00003212509,0.00002231656,0.0000243219],"domain_scores_gemma":[0.9999018,0.00002789818,0.00001250192,0.00001161158,0.00003486668,0.00001121078],"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":[0.0002475864,0.0002891769,0.004676973,0.0001084815,0.0001591367,0.0001564299,0.00005825063,0.5983219,0.02139433,0.003486138,0.005973298,0.3651283],"study_design_scores_gemma":[0.000003044677,0.00001804888,0.0002065431,0.000003571575,0.000008728701,0.00001154427,0.000003584572,0.9979768,0.001128139,0.0003947714,0.0002425961,0.000002605174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1775506,0.001510882,0.8092847,0.0006652629,0.0001758704,0.0001058835,0.000550703,0.003105835,0.007050222],"genre_scores_gemma":[0.9123617,0.0006314617,0.07823634,0.0003626455,0.00005559784,0.00006273147,0.001069439,0.0000819022,0.007138141],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01036159,"threshold_uncertainty_score":0.02060252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01769038214491304,"score_gpt":0.2608757815040045,"score_spread":0.2431853993590915,"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."}}