{"id":"W3196399896","doi":"10.1145/3460421.3480417","title":"Self-supervised Human Activity Recognition by Learning to Predict Cross-Dimensional Motion","year":2021,"lang":"en","type":"article","venue":"","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Activity recognition; Computer science; Accelerometer; Artificial intelligence; Leverage (statistics); Pattern recognition (psychology); Convolutional neural network; Transfer of learning; Machine learning; Convolution (computer science); Artificial neural network; Task (project management); Motion (physics); Dimension (graph theory); Mathematics","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":[0.0005628681,0.001060406,0.0009113559,0.0009366165,0.0001820737,0.0004404127,0.001205084,0.0006484771,0.001197796],"category_scores_gemma":[0.001611144,0.0003219776,0.0006401565,0.0008351185,0.0003542023,0.0008998373,0.0007475021,0.0008839003,0.001103201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003274797,"about_ca_system_score_gemma":0.0005050176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002551457,"about_ca_topic_score_gemma":0.00694519,"domain_scores_codex":[0.999387,0.0001118402,0.00003313721,0.0003259499,0.00008207165,0.0000599578],"domain_scores_gemma":[0.9992998,0.0001801203,0.0001173808,0.0001863575,0.0001620026,0.00005433528],"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":[0.0003980359,0.001018756,0.02845853,0.000179177,0.0003088693,0.0001624423,0.0001591253,0.1157987,0.01971278,0.001604271,0.01340457,0.8187948],"study_design_scores_gemma":[0.00001565635,0.0001032874,0.008036058,0.00001543078,0.00001932004,0.00008289063,0.00002562132,0.9818025,0.005628226,0.002743444,0.001512319,0.00001522661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1327958,0.0008717379,0.8543951,0.0003318715,0.0001835567,0.0001674931,0.001535277,0.006143363,0.003575859],"genre_scores_gemma":[0.8386585,0.0003378662,0.1511039,0.0003339908,0.000164819,0.000215332,0.004167003,0.0001337357,0.004884816],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002551457,"threshold_uncertainty_score":0.00507319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03142720996502948,"score_gpt":0.2789294444342768,"score_spread":0.2475022344692473,"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."}}