{"id":"W3034810086","doi":"10.1007/s11390-020-0405-6","title":"Two-Stream Temporal Convolutional Networks for Skeleton-Based Human Action Recognition","year":2020,"lang":"en","type":"article","venue":"Journal of Computer Science and Technology","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Skeleton (computer programming); Feature (linguistics); Leverage (statistics); Convolutional neural network; Feature vector; Feature learning; Representation (politics); RGB color model; Computer vision","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005006007,0.0001047433,0.000183182,0.0005063683,0.0003545391,0.000174084,0.0005318173,0.00008368606,0.000005572798],"category_scores_gemma":[0.00004779833,0.00009463845,0.00005852768,0.0009093712,0.000297213,0.0009110168,0.00009077504,0.0002339549,0.000003658591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004981855,"about_ca_system_score_gemma":0.0002464741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001598802,"about_ca_topic_score_gemma":0.000001768139,"domain_scores_codex":[0.9988495,0.00002262674,0.0003413038,0.0002669354,0.0002968115,0.0002228598],"domain_scores_gemma":[0.9984322,0.00005425619,0.0003639995,0.0001159655,0.0009024956,0.000131038],"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":[0.00004521095,0.0001638905,0.00121197,0.00003177696,0.00003220083,0.00002541378,0.00009601139,0.0007188796,0.01168253,0.01465254,0.002395122,0.9689445],"study_design_scores_gemma":[0.002506302,0.002537407,0.001256624,0.0000794562,0.00002474421,0.0002435824,0.00003970845,0.9366352,0.02069201,0.03154825,0.004136355,0.0003003668],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1597555,0.0000377679,0.8336591,0.005949481,0.0003819886,0.0001069678,0.000001385199,0.00008032554,0.0000274584],"genre_scores_gemma":[0.9261118,0.000006395174,0.07240305,0.001095081,0.000369983,0.000004831943,0.000002888345,0.000004018917,0.0000020157],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9686441,"threshold_uncertainty_score":0.3859244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0384129619373278,"score_gpt":0.2850209255017652,"score_spread":0.2466079635644374,"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."}}