{"id":"W2949163612","doi":"10.48550/arxiv.1903.02025","title":"Crowd Counting Using Scale-Aware Attention Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; ShanghaiTech University; Nvidia","keywords":"Benchmark (surveying); Computer science; Scale (ratio); Artificial intelligence; Image (mathematics); Pixel; Focus (optics); Computer vision; Pattern recognition (psychology); Geography; Cartography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008536812,0.0003417764,0.0004273217,0.0002319491,0.0002374487,0.0003069316,0.001563558,0.000412423,0.00001224468],"category_scores_gemma":[0.00002217732,0.0004137138,0.0002983232,0.0006492898,0.00007196103,0.0005732565,0.001852741,0.0007563813,0.00005797926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002288014,"about_ca_system_score_gemma":0.0001734332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002114504,"about_ca_topic_score_gemma":0.00004120514,"domain_scores_codex":[0.9975578,0.0003203453,0.0002518463,0.001252703,0.0001214571,0.0004958311],"domain_scores_gemma":[0.997698,0.0001537338,0.0004048843,0.001388878,0.0002441877,0.0001102989],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009234354,0.00003075013,0.08934758,0.00008478456,0.00005980013,0.0001012875,0.00004405241,0.9047382,0.00003819355,0.004078628,0.00005673783,0.001410717],"study_design_scores_gemma":[0.000280069,0.00001532883,0.01423108,0.0002298199,0.00004640924,0.000008424761,0.00002258327,0.9810989,0.00002147319,0.003452805,0.0001304548,0.0004626604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2749102,0.0000656584,0.7223176,0.00002203924,0.001652836,0.0001808112,0.000003810925,0.0002294775,0.0006176283],"genre_scores_gemma":[0.9905753,0.00008414662,0.008475599,0.00008750246,0.0002065151,3.201583e-7,0.00001600079,0.00002713412,0.0005275142],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7156651,"threshold_uncertainty_score":0.9998315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09883004615290243,"score_gpt":0.2235977910602648,"score_spread":0.1247677449073624,"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."}}