{"id":"W2173996720","doi":"","title":"Semi-supervised Learning with Encoder-Decoder Recurrent Neural Networks: Experiments with Motion Capture Sequences","year":2015,"lang":"en","type":"preprint","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Discriminative model; Encoder; Recurrent neural network; Artificial intelligence; Encoding (memory); Machine learning; Autoencoder; Regularization (linguistics); Sequence (biology); Feature learning; Pattern recognition (psychology); Supervised learning; Artificial neural network; Motion capture; Motion (physics); Sequence learning","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":[0.003371136,0.001760171,0.001123401,0.0006273886,0.0006233624,0.0005689022,0.001795036,0.001495231,0.001756393],"category_scores_gemma":[0.01070128,0.0004867825,0.0008526426,0.0008019555,0.0008913144,0.001489753,0.001003215,0.001884884,0.0006998716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008516922,"about_ca_system_score_gemma":0.000850819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01343998,"about_ca_topic_score_gemma":0.01697894,"domain_scores_codex":[0.9977505,0.001018792,0.0001904166,0.0005280908,0.0003261109,0.0001861014],"domain_scores_gemma":[0.9942079,0.003391452,0.0003708198,0.000937009,0.000816578,0.0002762302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003429349,0.004020063,0.008919477,0.001148062,0.0008472045,0.0005428348,0.0006724866,0.5293378,0.02016255,0.001632041,0.01432502,0.4149632],"study_design_scores_gemma":[0.0001417168,0.001021928,0.003047686,0.00003760089,0.000059124,0.0001122934,0.0001212093,0.9798015,0.01268006,0.001694109,0.001241308,0.00004143576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9245442,0.001999669,0.06037641,0.0005874104,0.0003196035,0.0004541634,0.00198873,0.004509659,0.005220098],"genre_scores_gemma":[0.9360891,0.0003170752,0.05461292,0.0002390508,0.00005388194,0.0002385821,0.004880576,0.0001779223,0.003390846],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01343998,"threshold_uncertainty_score":0.0267235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02352876789836961,"score_gpt":0.2500587755150337,"score_spread":0.2265300076166641,"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."}}