{"id":"W4200602317","doi":"10.1016/j.neucom.2021.12.027","title":"Towards more effective PRM-based crowd counting via a multi-resolution fusion and attention network","year":2021,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Department of Agriculture","keywords":"Computer science; Benchmark (surveying); Margin (machine learning); Artificial intelligence; Feature (linguistics); Task (project management); Pattern recognition (psychology); Machine learning; Data mining","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":[],"consensus_categories":[],"category_scores_codex":[0.001060872,0.0001926899,0.0002351776,0.00006666495,0.0004765337,0.0002451231,0.0002255172,0.00008460663,0.000001349164],"category_scores_gemma":[0.0002016674,0.0002002456,0.00008987322,0.0006246498,0.00003849608,0.0002524745,0.0003646642,0.0002659732,0.000004810085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004056269,"about_ca_system_score_gemma":0.00006460826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003423896,"about_ca_topic_score_gemma":0.00001304058,"domain_scores_codex":[0.9978263,0.0005166653,0.0002756165,0.0006714237,0.0002818471,0.0004281509],"domain_scores_gemma":[0.9988252,0.0003934808,0.0001763251,0.000328728,0.0001987134,0.00007757884],"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":[0.00002126097,0.0001418353,0.08889605,0.000217813,0.00002908011,0.0002008313,0.000435751,0.07692326,0.02574466,0.0005872092,0.00007307682,0.8067292],"study_design_scores_gemma":[0.0004908126,0.00003713732,0.3291197,0.0001289428,0.000005964683,0.00004204273,0.000004240635,0.6684307,0.001249607,0.0001468614,0.0002007169,0.0001433084],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2446118,0.0002294436,0.7537975,0.0003173301,0.0005432269,0.0001954573,4.003697e-7,0.0002273902,0.00007748708],"genre_scores_gemma":[0.7142525,0.000004740865,0.2849498,0.0005253283,0.0002326798,0.000009027932,0.000004322081,0.00001470003,0.000006932898],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8065858,"threshold_uncertainty_score":0.8165779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01810069708717075,"score_gpt":0.2871323211630011,"score_spread":0.2690316240758304,"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."}}