{"id":"W4386108371","doi":"10.1109/tmm.2023.3307933","title":"Learning Representations by Contrastive Spatio-Temporal Clustering for Skeleton-Based Action Recognition","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Cluster analysis; Artificial intelligence; Discriminative model; Feature learning; Pattern recognition (psychology); Regularization (linguistics); Machine 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002595047,0.0001956253,0.0001728847,0.0004305318,0.000618465,0.0001510601,0.0001739027,0.0001275356,0.0001222371],"category_scores_gemma":[0.00004214686,0.0002222193,0.0001657317,0.0006052199,0.00004405584,0.0006786138,0.000001806799,0.0003095105,0.000507722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001046502,"about_ca_system_score_gemma":0.00006756557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008533985,"about_ca_topic_score_gemma":0.00015946,"domain_scores_codex":[0.9984378,0.0001251662,0.0003266539,0.0004985408,0.0002784242,0.0003334746],"domain_scores_gemma":[0.9986064,0.000702398,0.0001526705,0.0002094165,0.000201102,0.0001279919],"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":[0.0001834037,0.0003009857,0.0000409894,0.00006060754,0.00008461936,0.000006230609,0.001058905,0.05493648,0.01203603,0.000005290249,0.004807136,0.9264793],"study_design_scores_gemma":[0.001614909,0.0002732141,0.0001762126,0.0000516213,0.00003179514,0.000002984299,0.0002346363,0.9074355,0.08757323,0.0002057121,0.002120505,0.0002796204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02814288,0.000002939977,0.968155,0.0005947481,0.00125623,0.0006351012,0.0001337135,0.0009527325,0.0001267149],"genre_scores_gemma":[0.9814731,0.00002666451,0.01583235,0.0002049115,0.000135099,0.0006604529,0.0006150939,0.00003506071,0.00101726],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9533302,"threshold_uncertainty_score":0.906184,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04889612834000338,"score_gpt":0.3053683181410561,"score_spread":0.2564721898010527,"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."}}