{"id":"W3170523166","doi":"10.1109/vtc2021-spring51267.2021.9448692","title":"Multimodal Machine Learning for Pedestrian Detection","year":2021,"lang":"en","type":"article","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University","funders":"","keywords":"Pedestrian detection; Computer science; Pedestrian; Artificial intelligence; Convolutional neural network; Object detection; Computer vision; Focus (optics); Context (archaeology); Deep learning; Cluster analysis; Machine learning; Pattern recognition (psychology); Engineering","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":[0.001458757,0.000753612,0.0007082809,0.001359388,0.0004967107,0.0006496066,0.000705003,0.0009150656,0.005713043],"category_scores_gemma":[0.003078418,0.0002252941,0.0007157623,0.0009158236,0.0003117253,0.0009022632,0.0007636346,0.0009404155,0.001981112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008873761,"about_ca_system_score_gemma":0.0005543026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004690283,"about_ca_topic_score_gemma":0.006746316,"domain_scores_codex":[0.9993404,0.0002433786,0.00002300388,0.0001538013,0.0001220183,0.0001174126],"domain_scores_gemma":[0.999284,0.000289108,0.00005486014,0.0001043079,0.0002223544,0.00004537486],"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":[0.0003937305,0.0003056079,0.006169292,0.0001857035,0.0001227561,0.0001210038,0.00008415085,0.07448535,0.008521982,0.004616019,0.01592802,0.8890664],"study_design_scores_gemma":[0.000008859401,0.00008835873,0.002330725,0.00002472889,0.00002274236,0.0000794099,0.00003325136,0.9838207,0.00438016,0.005805261,0.003387519,0.00001832033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09541677,0.003692593,0.8812638,0.001336254,0.0003921618,0.0002454486,0.001301972,0.005723947,0.01062714],"genre_scores_gemma":[0.8090388,0.0008185453,0.1802537,0.0004411398,0.0001828018,0.0001885765,0.001630401,0.0001233971,0.007322612],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005713043,"threshold_uncertainty_score":0.01911205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03129910344959924,"score_gpt":0.3017127363908818,"score_spread":0.2704136329412826,"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."}}