{"id":"W4226369513","doi":"10.1016/j.patcog.2023.109830","title":"CrowdMLP: Weakly-supervised crowd counting via multi-granularity MLP","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph; Memorial University of Newfoundland","funders":"Zhejiang Sci-Tech University; China Postdoctoral Science Foundation; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Granularity; Computer science; Cardinality (data modeling); Pattern recognition (psychology); Artificial intelligence; Feature (linguistics); Data mining; Spatial analysis; Machine learning; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001401013,0.0002042893,0.0002292895,0.000210942,0.0002611413,0.0002813652,0.0004955592,0.0001207324,0.00007147487],"category_scores_gemma":[0.0001389923,0.000212749,0.0001287017,0.0007692195,0.00003522865,0.0006312567,0.0001806153,0.0002482174,0.002354702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003489284,"about_ca_system_score_gemma":0.00002766621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002163833,"about_ca_topic_score_gemma":0.0001189366,"domain_scores_codex":[0.9979922,0.000280805,0.0003329007,0.0005632716,0.0003456488,0.0004852453],"domain_scores_gemma":[0.998893,0.0002480617,0.0001177391,0.0004614325,0.0001831158,0.00009671002],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000004130024,0.00007169003,0.03752663,0.00007334795,0.0000237097,0.00006053171,0.0004341414,0.00001100535,0.00725844,0.000005633844,0.0002984773,0.9542323],"study_design_scores_gemma":[0.002114886,0.0001199568,0.5803127,0.0002634074,0.000033637,0.00007405565,0.00007941381,0.3725231,0.0336594,0.007907392,0.001735764,0.001176304],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2471098,0.00003340152,0.7501715,0.000445439,0.0008628252,0.0001769426,0.0000183098,0.0008234445,0.0003583414],"genre_scores_gemma":[0.9632253,0.00004352633,0.03539799,0.0008104194,0.000222212,0.00005705886,0.0001296394,0.00003052432,0.00008330972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.953056,"threshold_uncertainty_score":0.9984221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07720168428992544,"score_gpt":0.3076822966566913,"score_spread":0.2304806123667658,"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."}}