{"id":"W2937934951","doi":"10.1109/crv.2019.00016","title":"Human Motion Prediction Via Pattern Completion in Latent Representation Space","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Autoencoder; Artificial intelligence; Representation (politics); Motion (physics); Computer science; Sequence (biology); Inference; Latent variable; Construct (python library); Pattern recognition (psychology); Feature learning; Machine learning; Motion capture; Artificial neural network","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":[0.000657502,0.0005988965,0.0007545117,0.0004714221,0.0001819845,0.0005177988,0.0009452298,0.0007524388,0.001487795],"category_scores_gemma":[0.002297775,0.0004225772,0.0008623855,0.0005834823,0.0008242241,0.001425365,0.0008417095,0.001561661,0.0003738298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004949723,"about_ca_system_score_gemma":0.000677943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005365611,"about_ca_topic_score_gemma":0.004592815,"domain_scores_codex":[0.9996994,0.00007787276,0.00001309638,0.0001154833,0.00005359114,0.0000405434],"domain_scores_gemma":[0.9991456,0.0004340961,0.0001292694,0.0001312722,0.0001004316,0.00005937556],"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":[0.0002171809,0.0001340308,0.002014448,0.000106145,0.0001050177,0.0001189073,0.0001517744,0.8100605,0.01603439,0.02599712,0.002079436,0.1429812],"study_design_scores_gemma":[0.000003399286,0.00001339359,0.0001379797,0.000002086616,0.000002600211,0.000007778031,0.000002191696,0.9936333,0.0006256837,0.005453375,0.000114996,0.0000032933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01805976,0.0001147483,0.9809884,0.000126008,0.00001714625,0.00001705795,0.00007083767,0.0003143246,0.0002916443],"genre_scores_gemma":[0.7186031,0.0003692106,0.2757822,0.0001615246,0.00009412236,0.0001359394,0.0006005791,0.0001505413,0.004102695],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005365611,"threshold_uncertainty_score":0.01066875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04926868660489776,"score_gpt":0.289167151222024,"score_spread":0.2398984646171263,"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."}}