{"id":"W3152390103","doi":"10.1016/j.knosys.2021.106990","title":"A robust and fast multispectral pedestrian detection deep network","year":2021,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"National Natural Science Foundation of China","keywords":"Multispectral image; Pedestrian detection; Computer science; Artificial intelligence; Kernel (algebra); Feature (linguistics); Pattern recognition (psychology); Computer vision; Pyramid (geometry); Convolutional neural network; Representation (politics); Receptive field; Field (mathematics); Pedestrian; Geography; Mathematics","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":[0.001035402,0.0002130323,0.0003367468,0.00009187603,0.0002946857,0.0004532507,0.0003004583,0.0001301727,0.000004876001],"category_scores_gemma":[0.0001331244,0.0002093934,0.00009864608,0.0007975124,0.0000432725,0.0002167136,0.00009259408,0.0002104719,0.00004933248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007964803,"about_ca_system_score_gemma":0.0001842236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008354949,"about_ca_topic_score_gemma":0.001534207,"domain_scores_codex":[0.9976429,0.0007594883,0.0003426103,0.000608702,0.0001891721,0.0004571235],"domain_scores_gemma":[0.9984931,0.0003937635,0.0001176288,0.0006033455,0.0002224295,0.0001697065],"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":[0.00009167283,0.0006760249,0.0786121,0.001509897,0.0002979041,0.0007504403,0.003139668,0.1249737,0.01006474,0.01118135,0.001110326,0.7675922],"study_design_scores_gemma":[0.001540317,0.0001414534,0.01934859,0.0002500327,0.00002169538,0.0002161348,0.0001191902,0.9627142,0.005038532,0.0002688117,0.009800595,0.0005404633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01451675,0.00644672,0.9735306,0.00009376321,0.002960233,0.0002039778,0.000001769347,0.0002981767,0.001948052],"genre_scores_gemma":[0.9751097,0.00001905969,0.02374043,0.00003672426,0.0007574133,0.00004036194,0.000004218314,0.00002046904,0.0002716453],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9605929,"threshold_uncertainty_score":0.8538816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03498350239768094,"score_gpt":0.2641578378356488,"score_spread":0.2291743354379679,"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."}}