{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007707737,0.0009526241,0.0008678036,0.000705732,0.0001852556,0.0007148001,0.001257052,0.0006930478,0.003055399],"category_scores_gemma":[0.002194354,0.0003200886,0.0006956189,0.0005345395,0.0006042859,0.00111533,0.001270237,0.0009541333,0.001075796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005496033,"about_ca_system_score_gemma":0.0005699782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006954631,"about_ca_topic_score_gemma":0.008208796,"domain_scores_codex":[0.9992769,0.00009259037,0.00002267887,0.0003644612,0.0001290728,0.0001142935],"domain_scores_gemma":[0.9992749,0.0002105108,0.0000987338,0.0001936153,0.0001349306,0.00008728755],"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":[0.000493043,0.0002031096,0.004015183,0.0001636551,0.0001384973,0.0001892514,0.0001636105,0.04775597,0.1341479,0.002497274,0.006960949,0.8032715],"study_design_scores_gemma":[0.00002467202,0.0002052214,0.01076245,0.00002746141,0.00007096722,0.0002626522,0.00003441934,0.9291673,0.05094883,0.005818116,0.002642409,0.0000355707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09154256,0.001017615,0.8956726,0.0003776001,0.0002252811,0.00008004237,0.0005334236,0.006104395,0.004446405],"genre_scores_gemma":[0.8703454,0.0004001666,0.1209812,0.0004132037,0.0001661654,0.0000579923,0.0008623808,0.0002612604,0.006512209],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006954631,"threshold_uncertainty_score":0.01382834,"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."}}