{"id":"W4312416140","doi":"10.1109/cvpr52688.2022.01562","title":"SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Leverage (statistics); Cluster analysis; Artificial intelligence; False positive paradox; Key (lock); Pattern recognition (psychology); Annotation","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":[0.003171481,0.002682211,0.001969895,0.002701944,0.001071167,0.001061375,0.00443419,0.002193332,0.003613743],"category_scores_gemma":[0.007066883,0.0008599369,0.001566023,0.002025206,0.001139645,0.002179418,0.001938022,0.002814902,0.00273869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001774391,"about_ca_system_score_gemma":0.002172741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01135263,"about_ca_topic_score_gemma":0.01952158,"domain_scores_codex":[0.9973511,0.0007099879,0.0001212811,0.0009389312,0.0006714002,0.0002073725],"domain_scores_gemma":[0.9969465,0.001053841,0.0002228368,0.0006981029,0.0009025778,0.0001760567],"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":[0.0006143449,0.000656479,0.002683653,0.0003697088,0.0003006734,0.0001595366,0.0002963421,0.1898991,0.01288912,0.004850457,0.05295655,0.7343241],"study_design_scores_gemma":[0.00002691195,0.00005907553,0.0003194458,0.00000860444,0.00001082309,0.00003860474,0.00002569836,0.9904828,0.003651975,0.003829139,0.001532373,0.00001459313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01087164,0.0003986618,0.9696524,0.0001545832,0.00008726258,0.0003780614,0.0006312994,0.01652519,0.00130101],"genre_scores_gemma":[0.1430561,0.0001863614,0.8448914,0.0004164387,0.0001213284,0.000724622,0.00575974,0.001038101,0.003805967],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01135263,"threshold_uncertainty_score":0.02257311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06442381366281381,"score_gpt":0.2985487784939969,"score_spread":0.2341249648311831,"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."}}