{"id":"W2745957831","doi":"10.1109/iccvw.2017.77","title":"Human Action Recognition: Pose-Based Attention Draws Focus to Hands","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Discriminative model; Computer science; Artificial intelligence; Recurrent neural network; Action recognition; Action (physics); Machine learning; RGB color model; Focus (optics); Contrast (vision); Pattern recognition (psychology); Artificial neural network; Class (philosophy)","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","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003874477,0.0003627455,0.0003311441,0.0005198194,0.000869686,0.001723863,0.00106417,0.0003920883,0.0005017444],"category_scores_gemma":[0.00003647535,0.0003766959,0.0002997381,0.0001257875,0.00003816946,0.0007091062,0.0005979304,0.000561599,0.001784385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001753816,"about_ca_system_score_gemma":0.0001556276,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002442593,"about_ca_topic_score_gemma":0.0002456202,"domain_scores_codex":[0.9976109,0.000116322,0.0004432375,0.001015602,0.0004694478,0.0003445405],"domain_scores_gemma":[0.9975392,0.00002578378,0.0004466481,0.001359156,0.0004073401,0.0002219081],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003366691,0.000460568,0.0002023416,0.0002379395,0.0001208828,0.00004668548,0.000202722,0.0001059017,0.004963824,0.001855212,0.04386083,0.9479094],"study_design_scores_gemma":[0.01010563,0.003798477,0.06265304,0.005144253,0.0005972107,0.0001399914,0.0001492858,0.03967559,0.2553619,0.5626789,0.05092519,0.008770527],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1885722,0.00001939352,0.7427895,0.005235592,0.004431524,0.001191764,0.0000367076,0.00134391,0.0563794],"genre_scores_gemma":[0.9806099,0.00001009899,0.0109992,0.0008573778,0.001192044,0.0002554553,0.0003432596,0.00003365941,0.005698995],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9391389,"threshold_uncertainty_score":0.9998685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1030405657052701,"score_gpt":0.3401257621946269,"score_spread":0.2370851964893567,"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."}}