{"id":"W4390891830","doi":"10.1016/j.trc.2023.104465","title":"Unlabeled scene adaptive crowd counting via meta-ensemble learning","year":2024,"lang":"en","type":"article","venue":"Transportation Research Part C Emerging Technologies","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Consistency (knowledge bases); Process (computing); Machine learning; Ensemble learning; Computer vision; Pattern recognition (psychology)","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":[0.004136929,0.0002467877,0.0003817041,0.0008023417,0.0005827735,0.0003874948,0.001021488,0.0001830661,0.0000369708],"category_scores_gemma":[0.0003531603,0.0002132946,0.00019205,0.002913012,0.0002498067,0.0008899202,0.00007931644,0.001245223,0.0001015815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006531191,"about_ca_system_score_gemma":0.0001341211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002006243,"about_ca_topic_score_gemma":0.0002154985,"domain_scores_codex":[0.9966049,0.0003415865,0.0004552814,0.0008225901,0.0009580635,0.000817629],"domain_scores_gemma":[0.9979858,0.0008759554,0.00007662929,0.0005865046,0.0004199826,0.0000551279],"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":[0.00004253948,0.0001094364,0.005434192,0.0004409619,0.001619512,0.0007133061,0.002767705,0.00602384,0.01582465,0.2234551,0.002775038,0.7407937],"study_design_scores_gemma":[0.000876709,0.0008570908,0.005165215,0.0007646741,0.0003765105,0.00002272316,0.0034165,0.4123259,0.1809115,0.1610831,0.2323932,0.001806806],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01544507,0.009124229,0.9614115,0.0053327,0.0003745286,0.0003658096,0.000007108143,0.00722971,0.0007093708],"genre_scores_gemma":[0.9179865,0.0008094995,0.0805255,0.0000180929,0.00003263843,0.000193677,0.00001432241,0.00003129367,0.000388458],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9025415,"threshold_uncertainty_score":0.86979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1581512962531223,"score_gpt":0.4021177562005236,"score_spread":0.2439664599474013,"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."}}