{"id":"W3003950743","doi":"10.48550/arxiv.2002.00264","title":"Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Computer science; Artificial intelligence; Shot (pellet); Computer vision; Adaptation (eye); One shot; Code (set theory); Context (archaeology)","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":[0.001081457,0.0005185446,0.0008801753,0.000265097,0.0004133032,0.0003409872,0.001975707,0.0003226929,0.00004349492],"category_scores_gemma":[0.000195124,0.0005850372,0.0006006215,0.001048487,0.0001158819,0.0006050844,0.002794686,0.001445713,0.00006500736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002303176,"about_ca_system_score_gemma":0.0003454619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003680918,"about_ca_topic_score_gemma":0.00002768553,"domain_scores_codex":[0.9964211,0.000764291,0.0003237302,0.001717539,0.0002038442,0.0005695162],"domain_scores_gemma":[0.9975453,0.0003632618,0.0005598887,0.001006064,0.0002982676,0.000227188],"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":[0.00005461692,0.00006733897,0.006539176,0.0001468521,0.001996308,0.00127426,0.0006745474,0.9347597,0.0005243364,0.05198406,0.00006497599,0.001913881],"study_design_scores_gemma":[0.0003314181,0.00005808532,0.001155356,0.00008944103,0.0006538353,0.00001162663,0.0000915389,0.9784139,0.000510391,0.01725944,0.0006796246,0.0007453054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05909949,0.0002610116,0.9365262,0.0001318466,0.0006675433,0.0002255318,0.00000791596,0.0005187806,0.002561625],"genre_scores_gemma":[0.9321429,0.00008055765,0.06713479,0.0001842311,0.000169559,7.879123e-7,0.000007259961,0.0000382162,0.000241717],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8730434,"threshold_uncertainty_score":0.9996601,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3713096575017266,"score_gpt":0.258587451808368,"score_spread":0.1127222056933586,"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."}}