{"id":"W4382466151","doi":"10.1609/aaai.v37i1.25194","title":"Frequency Selective Augmentation for Video Representation Learning","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Korea Advanced Institute of Science and Technology","keywords":"Computer science; Generality; Representation (politics); Feature learning; Focus (optics); Artificial intelligence; Machine learning; Pattern recognition (psychology)","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":[0.001016485,0.0009487672,0.0007593083,0.0007873587,0.0003107257,0.000530555,0.00153005,0.0009430588,0.002023167],"category_scores_gemma":[0.004764172,0.0003803152,0.0007731764,0.0007905659,0.0008293664,0.001770702,0.001348986,0.001771153,0.0007559641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006373677,"about_ca_system_score_gemma":0.0005847338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002795679,"about_ca_topic_score_gemma":0.002975788,"domain_scores_codex":[0.9992675,0.00022393,0.00002738758,0.0002364405,0.0001701449,0.0000746408],"domain_scores_gemma":[0.998362,0.0007706877,0.0001728039,0.0003932922,0.0002390072,0.00006219113],"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":[0.0003611689,0.0003619306,0.001670423,0.0001863068,0.00008807579,0.0001084291,0.0001760611,0.3148595,0.0415118,0.01004005,0.00814909,0.6224871],"study_design_scores_gemma":[0.000007301937,0.0000564891,0.0002393518,0.000007086763,0.000006962954,0.00003545609,0.00001155216,0.9887898,0.005377653,0.004470708,0.0009893683,0.000008212937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02568623,0.0003902998,0.9698771,0.0002071339,0.00007140649,0.00005704805,0.0001607488,0.002223472,0.001326562],"genre_scores_gemma":[0.6710294,0.0004474221,0.3226696,0.000337942,0.0001747998,0.0002447905,0.001212585,0.000320775,0.003562777],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002795679,"threshold_uncertainty_score":0.006768167,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1196440185864678,"score_gpt":0.3445177692375753,"score_spread":0.2248737506511075,"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."}}