{"id":"W3196892597","doi":"10.48550/arxiv.2109.02137","title":"Efficient Action Recognition Using Confidence Distillation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Task (project management); Machine learning; Artificial intelligence; Representation (politics); Action recognition; Overhead (engineering); Aggregate (composite); Action (physics); Distillation; Sample (material); Pattern recognition (psychology); Artificial neural network; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00176536,0.001372899,0.001898288,0.001012519,0.0005340786,0.001511092,0.003006409,0.001537474,0.004968785],"category_scores_gemma":[0.008091323,0.0006488258,0.001034603,0.0009953532,0.001042941,0.002955322,0.002588323,0.003282849,0.002194278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001079493,"about_ca_system_score_gemma":0.001711186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007693653,"about_ca_topic_score_gemma":0.008656311,"domain_scores_codex":[0.9980318,0.0004122959,0.00009737934,0.0006624965,0.0005715807,0.0002244882],"domain_scores_gemma":[0.9975037,0.001225858,0.0001897534,0.0005740209,0.0003873544,0.0001193594],"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":[0.0004952797,0.0002022818,0.001800653,0.0001582112,0.00007710696,0.0001451595,0.0001334995,0.2470755,0.009500061,0.0153121,0.009199757,0.7159004],"study_design_scores_gemma":[0.00001324963,0.00002729877,0.0001408702,0.00000893802,0.000007146435,0.00002842277,0.000009145652,0.9881179,0.003029501,0.007886733,0.0007199131,0.0000109962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02456929,0.0006981223,0.9634728,0.0005942018,0.0001067696,0.00007057734,0.0004063123,0.007636353,0.00244551],"genre_scores_gemma":[0.6446003,0.0003870057,0.3454174,0.0006757681,0.0002138746,0.0001860276,0.002188397,0.0004484528,0.005882825],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007693653,"threshold_uncertainty_score":0.01662225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2025058728526224,"score_gpt":0.2259309305121786,"score_spread":0.02342505765955616,"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."}}