{"id":"W2172806452","doi":"10.48550/arxiv.1511.04119","title":"Action Recognition using Visual Attention","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":360,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Task (project management); Action (physics); Focus (optics); Artificial intelligence; Action recognition; Recurrent neural network; Long short term memory; Visual attention; Deep neural networks; Term (time); Artificial neural network; Machine learning; Pattern recognition (psychology); Psychology; Cognition","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":[0.0004948058,0.001180223,0.0007704874,0.001082886,0.000236082,0.0007767832,0.001449923,0.001050947,0.002902675],"category_scores_gemma":[0.001653933,0.0003547501,0.001065128,0.0006644442,0.0005670746,0.001290588,0.0009885376,0.001267174,0.00117185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001191717,"about_ca_system_score_gemma":0.0007037273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0211387,"about_ca_topic_score_gemma":0.0217316,"domain_scores_codex":[0.9994453,0.00006876144,0.00001774848,0.0002643317,0.0001014211,0.0001024537],"domain_scores_gemma":[0.999599,0.0001298881,0.00006008708,0.00006874539,0.00009624845,0.00004606105],"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":[0.0005416182,0.000363577,0.005392905,0.0002268389,0.0002338153,0.0003151341,0.000162358,0.1478053,0.06125075,0.009130511,0.01945591,0.7551212],"study_design_scores_gemma":[0.00001392659,0.0001150073,0.003054049,0.000023803,0.00004617863,0.00009673996,0.00002057202,0.9762731,0.008182672,0.01022281,0.001930976,0.00002015376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09937164,0.003413352,0.8752736,0.001500905,0.0005950576,0.0001387528,0.001666975,0.006981291,0.01105838],"genre_scores_gemma":[0.9059344,0.0009489451,0.07898249,0.0009422188,0.0002935221,0.0000905866,0.001981704,0.0001615797,0.01066453],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0211387,"threshold_uncertainty_score":0.04203129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2780461280829146,"score_gpt":0.2518824955850256,"score_spread":0.02616363249788894,"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."}}