{"id":"W2992457155","doi":"10.1109/iccvw.2019.00189","title":"Interpretable Spatio-Temporal Attention for Video Action Recognition","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Discriminative model; Interpretability; Computer science; Artificial intelligence; Pattern recognition (psychology); Salient; Action recognition; Set (abstract data type); Feature extraction; Minimum bounding box; Feature (linguistics); Bounding overwatch; Machine learning; Computer vision; Image (mathematics); Class (philosophy)","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":[0.0005003022,0.00101758,0.0005268546,0.0006282796,0.0001710779,0.0005375312,0.001255843,0.0008416457,0.002169744],"category_scores_gemma":[0.001809496,0.0002986239,0.0007477104,0.0004854734,0.00052753,0.001085457,0.0007222976,0.001265286,0.0006538564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001205954,"about_ca_system_score_gemma":0.0006568587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01120613,"about_ca_topic_score_gemma":0.01287786,"domain_scores_codex":[0.9997332,0.00004890381,0.00001089109,0.0001169092,0.00004600975,0.00004419764],"domain_scores_gemma":[0.9995795,0.0001714436,0.00006433699,0.00008618835,0.00006679801,0.00003169129],"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":[0.0004091611,0.0002769468,0.002258259,0.0001966023,0.0001367394,0.0002735055,0.0002035019,0.3533528,0.1073556,0.01194193,0.008068566,0.5155265],"study_design_scores_gemma":[0.000005422297,0.00003070555,0.0006211328,0.000006916188,0.00001438303,0.00003772797,0.00001126872,0.9849589,0.008017462,0.00554169,0.0007474215,0.000006932254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03104649,0.000543223,0.9621296,0.0003130315,0.00008443186,0.00004535892,0.0003409445,0.003938936,0.001557945],"genre_scores_gemma":[0.8328747,0.0005103822,0.1605808,0.0003357928,0.0001320489,0.0000931424,0.0009031336,0.0002057185,0.004364198],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01120613,"threshold_uncertainty_score":0.02228177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0665918228806321,"score_gpt":0.3027020723865421,"score_spread":0.23611024950591,"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."}}