{"id":"W2907241742","doi":"10.1007/s00521-018-3954-7","title":"Crowd density estimation based on classification activation map and patch density level","year":2019,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Density estimation; Artificial intelligence; Scale (ratio); Pattern recognition (psychology); Image (mathematics); Perspective (graphical); Regression; Artificial neural network; Discriminant; Task (project management); Mathematics; Statistics; Geography; Cartography","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":[0.0003684181,0.0001134985,0.0001235106,0.00006787337,0.0003072436,0.0001574339,0.0001491632,0.00005832144,9.976543e-7],"category_scores_gemma":[0.00002995374,0.0001108904,0.00002344824,0.0002176106,0.00003061598,0.0001758288,0.00006554999,0.0001479705,0.00002011606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002314273,"about_ca_system_score_gemma":0.00002047772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003610839,"about_ca_topic_score_gemma":0.000004056615,"domain_scores_codex":[0.9990221,0.0001003586,0.0001615496,0.0004240517,0.0001516504,0.0001403381],"domain_scores_gemma":[0.9989737,0.0003832001,0.0001200046,0.000379054,0.00008769611,0.00005632345],"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":[0.00001412248,0.0001051864,0.09362848,0.00009234689,0.000008442227,5.59557e-7,0.0001988412,0.008336998,0.01094308,0.03362526,0.0001306646,0.852916],"study_design_scores_gemma":[0.0001414595,0.00002477869,0.3530939,0.00001412011,0.000002265411,0.000002657674,0.000005746208,0.6436382,0.001593874,0.001259182,0.0001389936,0.00008483286],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4185461,0.000005460386,0.5799918,0.001026264,0.00004604939,0.0001927727,9.416275e-7,0.0001022989,0.00008831794],"genre_scores_gemma":[0.9424044,0.00000144915,0.05704269,0.0004497742,0.00004608342,0.00001153282,0.00001453228,0.000006136162,0.00002339063],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8528312,"threshold_uncertainty_score":0.4521979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04819773911735281,"score_gpt":0.3100122474674801,"score_spread":0.2618145083501273,"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."}}