{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001619442,0.0000880571,0.00007241652,0.0001501848,0.0001959072,0.0002300622,0.00004296393,0.00005110133,0.00004736311],"category_scores_gemma":[0.0000108606,0.00007537231,0.00004100462,0.0002038287,0.00002742226,0.00125473,0.000007446669,0.0001201771,0.0000481339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003977323,"about_ca_system_score_gemma":0.00004126876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002160079,"about_ca_topic_score_gemma":0.00002271818,"domain_scores_codex":[0.9992242,0.00003478463,0.0001356909,0.0003243132,0.0001471618,0.0001337883],"domain_scores_gemma":[0.9996628,0.0001213278,0.00003148961,0.00005282035,0.00008533944,0.00004619815],"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":[0.00006261191,0.00002773963,0.00008594317,0.0001221532,0.0000526877,0.000003816276,0.0005016007,0.00006372231,0.003887389,0.008570872,0.001436218,0.9851853],"study_design_scores_gemma":[0.002667551,0.001581352,0.003258042,0.0004367001,0.0001470781,0.0004111964,0.001374704,0.7833319,0.06891476,0.05667398,0.08027943,0.0009232934],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09138171,0.00005393886,0.9044874,0.00103366,0.0002237276,0.0002849665,0.00000312306,0.0005272932,0.00200422],"genre_scores_gemma":[0.98413,0.0001441151,0.01377725,0.0001363541,0.0001541279,0.00006656369,0.0001170391,0.0000165424,0.001457995],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9842619,"threshold_uncertainty_score":0.3073594,"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."}}