{"id":"W4312775149","doi":"10.1109/icpr56361.2022.9956432","title":"Efficient Action Recognition Using Confidence Distillation","year":2022,"lang":"en","type":"article","venue":"2022 26th International Conference on Pattern Recognition (ICPR)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Task (project management); Overhead (engineering); Action recognition; Aggregate (composite); CLIPS; Distillation; Action (physics); Artificial neural network; Pattern recognition (psychology); Computational complexity theory; Algorithm; 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":[0.001626202,0.001600992,0.002062072,0.00117657,0.0005664838,0.001544317,0.003168838,0.00145725,0.006453435],"category_scores_gemma":[0.007533863,0.0006674267,0.00103539,0.001067503,0.0009249296,0.002847435,0.002547424,0.003244165,0.00283246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009629361,"about_ca_system_score_gemma":0.001733917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007395845,"about_ca_topic_score_gemma":0.008503608,"domain_scores_codex":[0.997976,0.000324014,0.0001095569,0.0007093384,0.0006505064,0.0002305826],"domain_scores_gemma":[0.9977209,0.001000587,0.0001938176,0.0005213473,0.0004443912,0.0001189617],"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":[0.0004981431,0.0002101088,0.001462518,0.0001563398,0.00006968119,0.0001498144,0.0001128531,0.1672653,0.01182036,0.009307778,0.009740264,0.7992069],"study_design_scores_gemma":[0.00001835224,0.00003885544,0.0001917993,0.00001151384,0.00001056738,0.00003920907,0.00001229113,0.9872797,0.004829917,0.006434884,0.001117684,0.00001520664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02420047,0.0007621943,0.9589632,0.0005247099,0.0001394921,0.00009497297,0.0004908479,0.01188286,0.002941291],"genre_scores_gemma":[0.5545861,0.0004043038,0.4342173,0.0006818873,0.0002115774,0.0002086144,0.002748769,0.0005889767,0.006352474],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007395845,"threshold_uncertainty_score":0.02158886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1656069519237496,"score_gpt":0.3290349306601539,"score_spread":0.1634279787364042,"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."}}