{"id":"W4405427552","doi":"10.3390/a17120581","title":"Unsupervised Temporal Adaptation in Skeleton-Based Human Action Recognition","year":2024,"lang":"en","type":"article","venue":"Algorithms","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; University of Ottawa","keywords":"Skeleton (computer programming); Adaptation (eye); Computer science; Action recognition; Artificial intelligence; Human skeleton; Action (physics); Pattern recognition (psychology); Psychology; Neuroscience","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002665347,0.0001299197,0.0001102183,0.0004301158,0.0001126754,0.0002841116,0.0001655639,0.00009019554,0.0001381773],"category_scores_gemma":[0.00001014564,0.0001350706,0.00007133483,0.0006182823,0.00001902672,0.001036862,0.00001964591,0.0002053575,0.0004615506],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001126869,"about_ca_system_score_gemma":0.0000833149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002356407,"about_ca_topic_score_gemma":0.0001559281,"domain_scores_codex":[0.9988335,0.00008654527,0.0002577621,0.0003904642,0.0002320427,0.0001996268],"domain_scores_gemma":[0.9995968,0.00006257767,0.00004177052,0.0001785513,0.00006381145,0.00005643017],"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":[0.000004267004,0.00009800142,0.0000682627,0.0000553137,0.00001082011,0.00007917554,0.0004883354,0.0001337769,0.002015397,0.0006752806,0.0004648759,0.9959065],"study_design_scores_gemma":[0.0006887145,0.0001718353,0.001866418,0.0002178314,0.00001179952,0.0000203306,0.0001423363,0.9643739,0.009250333,0.01727231,0.005637844,0.0003463348],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2217585,0.0001423504,0.7722404,0.001086322,0.001410414,0.0003671608,0.00001227161,0.0009356964,0.002046879],"genre_scores_gemma":[0.9844813,0.00001355216,0.0145127,0.0002505055,0.0002520792,0.00006480524,0.0002088264,0.00001622257,0.0001999493],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9955602,"threshold_uncertainty_score":0.5932454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08183868303031432,"score_gpt":0.3128406169652574,"score_spread":0.2310019339349431,"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."}}