{"id":"W2783436923","doi":"10.1016/j.patcog.2018.12.009","title":"From superpixel to human shape modelling for carried object detection","year":2018,"lang":"en","type":"preprint","venue":"Pattern Recognition","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal; Université Laval","funders":"","keywords":"Codebook; Artificial intelligence; Computer science; Frame (networking); Pattern recognition (psychology); Computer vision; Object (grammar); Complement (music); Matching (statistics); Set (abstract data type); Object detection; Enhanced Data Rates for GSM Evolution; Scale (ratio); Mathematics; Geography","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001603198,0.0003290022,0.0002921309,0.0001793277,0.000317486,0.0002362036,0.0007881214,0.00025935,0.00003408819],"category_scores_gemma":[0.0000218696,0.0003826439,0.0001656609,0.0001955573,0.0000252417,0.0002496752,0.0006205087,0.000348249,0.0002212093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001544776,"about_ca_system_score_gemma":0.00003080582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002538693,"about_ca_topic_score_gemma":0.0001805382,"domain_scores_codex":[0.9976756,0.00006642158,0.0004246995,0.001231775,0.0002372052,0.0003643134],"domain_scores_gemma":[0.9982944,0.000156381,0.000228412,0.0008488111,0.0003253552,0.000146644],"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":[0.00002650007,0.00007615584,0.00005198364,0.00009097633,0.00006511006,0.000001930429,0.001074783,0.01759115,0.01382135,0.00001903458,0.0003644981,0.9668165],"study_design_scores_gemma":[0.0002691273,0.0001146223,0.0001336857,0.000202655,0.00004455859,0.000002380584,0.00001515226,0.8553284,0.03331817,0.1095203,0.0004773014,0.0005736377],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2552986,0.00001807199,0.7418231,0.0001838901,0.0007876357,0.00119153,0.0002783091,0.0003458716,0.00007303949],"genre_scores_gemma":[0.8904663,0.00001272366,0.1043847,0.0004955374,0.001881402,0.001835679,0.0008540204,0.00005493903,0.00001475478],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9662429,"threshold_uncertainty_score":0.9998626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08964945454133784,"score_gpt":0.3116208940914517,"score_spread":0.2219714395501138,"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."}}