{"id":"W3104886315","doi":"10.1155/2020/8848874","title":"A New Video-Based Crash Detection Method: Balancing Speed and Accuracy Using a Feature Fusion Deep Learning Framework","year":2020,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Government of Jiangsu Province; National Natural Science Foundation of China","keywords":"Computer science; Crash; Convolutional neural network; Artificial intelligence; Feature (linguistics); Deep learning; Computer vision; Feature extraction; Machine learning; Pattern recognition (psychology)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006287929,0.0001709046,0.0003207677,0.0001441469,0.0001574246,0.0001103258,0.0002067337,0.0001195183,0.000005013733],"category_scores_gemma":[0.0005503521,0.0001596709,0.000129255,0.000622263,0.00001078004,0.001165953,0.000006823624,0.000666237,5.640507e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004361258,"about_ca_system_score_gemma":0.0001031489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001016702,"about_ca_topic_score_gemma":0.00002074434,"domain_scores_codex":[0.9984919,0.0002057396,0.0004513586,0.0002777155,0.0003763015,0.000196942],"domain_scores_gemma":[0.9982264,0.0005532417,0.0006838981,0.000117373,0.0002119976,0.0002070677],"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":[0.0001702077,0.0000104034,0.005099263,0.00005629313,0.0000226967,0.00005543202,0.002901701,0.3986076,0.1434545,0.00007083663,0.000002028328,0.449549],"study_design_scores_gemma":[0.004287637,0.001173489,0.4260838,0.0009123531,0.0001847673,0.0001474112,0.0007267349,0.4685521,0.08802566,0.007172095,0.00198184,0.000752052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1954644,0.0003773592,0.8028534,0.0008590891,0.0003044111,0.00008568489,4.300134e-7,0.00005234137,0.000002902211],"genre_scores_gemma":[0.4713966,0.00004540574,0.5281795,0.0002146405,0.0001514707,2.458142e-7,0.000001079822,0.00001000178,0.000001062651],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.448797,"threshold_uncertainty_score":0.6511191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01878630148063203,"score_gpt":0.3128654528932765,"score_spread":0.2940791514126445,"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."}}