{"id":"W4408146280","doi":"10.1109/icmla61862.2024.00025","title":"ReL-SAR: Representation Learning for Skeleton Action Recognition with Convolutional Transformers and BYOL","year":2024,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Université du Québec","funders":"","keywords":"Computer science; Action recognition; Transformer; Artificial intelligence; Convolutional neural network; Skeleton (computer programming); Pattern recognition (psychology); Feature learning; Representation (politics); Computer vision; Engineering; Voltage; Electrical engineering; Class (philosophy)","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":[0.0009021169,0.001627797,0.001001442,0.001199768,0.0003735222,0.0009266253,0.002622281,0.0009203473,0.007866555],"category_scores_gemma":[0.002062415,0.000595262,0.001165499,0.0009048695,0.0008764388,0.002088718,0.002059262,0.002162755,0.004718835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009998108,"about_ca_system_score_gemma":0.001560226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007130042,"about_ca_topic_score_gemma":0.01332596,"domain_scores_codex":[0.9994578,0.00007050744,0.00002455638,0.0002531488,0.0001125055,0.00008152358],"domain_scores_gemma":[0.9994943,0.0001088075,0.00004383389,0.0002307868,0.00007946532,0.00004273807],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003892067,0.0002965034,0.001787699,0.0003567809,0.0001562781,0.0001498606,0.000115309,0.07721391,0.04320619,0.01747101,0.02938178,0.8294755],"study_design_scores_gemma":[0.00003816039,0.0001280529,0.0005492757,0.00002426839,0.00002867112,0.0001243003,0.00003574773,0.9547978,0.0215095,0.01485119,0.007891314,0.00002167998],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01050002,0.0002931374,0.9634343,0.0001260775,0.00006337957,0.0001169876,0.0007729518,0.02296725,0.001725906],"genre_scores_gemma":[0.2593882,0.0005404294,0.7170002,0.0004556867,0.00006414068,0.0003915507,0.01066341,0.002059487,0.009437074],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007866555,"threshold_uncertainty_score":0.02631629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04707326408014844,"score_gpt":0.2975582972517287,"score_spread":0.2504850331715802,"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."}}