{"id":"W4391188490","doi":"10.1016/j.eswa.2024.123228","title":"MetaUSACC: Unlabeled scene adaptation for crowd counting via meta-auxiliary learning","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"China Scholarship Council","keywords":"Computer science; Task (project management); Artificial intelligence; Adaptation (eye); Machine learning; Supervised learning; Computer vision; Pattern recognition (psychology); Artificial neural network","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":[0.001362868,0.0002192712,0.0003837857,0.0001585898,0.00041801,0.0005609154,0.0004608864,0.00007416501,0.000006227232],"category_scores_gemma":[0.00005352182,0.0001658254,0.0001468415,0.0008140621,0.0000328392,0.0005720954,0.00004755631,0.0001651582,0.00005684432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006124528,"about_ca_system_score_gemma":0.0001203815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001806048,"about_ca_topic_score_gemma":0.00001973614,"domain_scores_codex":[0.9981381,0.0001788114,0.0003985698,0.0006573787,0.0003150682,0.0003120633],"domain_scores_gemma":[0.9981283,0.0008145482,0.000145571,0.0005758075,0.0002530509,0.00008273074],"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":[0.00005450303,0.0003231839,0.0005740664,0.001472742,0.006971702,0.00003087082,0.009712785,0.0609065,0.03091611,0.4389953,0.005774075,0.4442682],"study_design_scores_gemma":[0.0001974194,0.00006990834,0.00005942785,0.00007680918,0.0001894514,0.00005245278,0.0001919609,0.7144555,0.001132682,0.0007396481,0.2824969,0.0003378216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00007589631,0.01263127,0.9839523,0.0006424381,0.0003036915,0.001148281,0.000005566396,0.0007563027,0.0004841923],"genre_scores_gemma":[0.641641,0.0000484237,0.3497228,0.0001178671,0.0003715893,0.007121194,0.00002766324,0.00004716997,0.0009023163],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.653549,"threshold_uncertainty_score":0.6762164,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0623486884662975,"score_gpt":0.3248349720059056,"score_spread":0.2624862835396081,"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."}}