{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003872314,0.0001173737,0.0001317093,0.000183502,0.0003183367,0.0001979872,0.0005604916,0.00004692296,0.00002995201],"category_scores_gemma":[0.000665717,0.00009921289,0.00009346116,0.000955129,0.00006684328,0.0006199784,0.00008933134,0.0001679046,0.0001593859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004690617,"about_ca_system_score_gemma":0.00005346086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002342143,"about_ca_topic_score_gemma":0.000005277607,"domain_scores_codex":[0.998763,0.00001901631,0.0003401456,0.0003641091,0.0002968553,0.0002169253],"domain_scores_gemma":[0.9986627,0.0001771785,0.0003193938,0.0001109864,0.0006903779,0.00003936074],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003192799,0.00005957632,0.0003819948,0.00003819302,0.00001954565,2.523129e-7,0.002534736,0.0002285474,0.1755085,0.6951664,0.0006290311,0.1254013],"study_design_scores_gemma":[0.00002982885,0.0001282616,0.0003865537,0.00006343664,0.000007504384,0.000001098334,0.0007061097,0.0668086,0.595575,0.3361497,0.00004350099,0.0001003454],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7341532,0.000009227485,0.2368462,0.005526812,0.001409064,0.001777669,0.00001003837,0.0007673525,0.0195004],"genre_scores_gemma":[0.9973026,0.00001640544,0.001980106,0.0001149351,0.00006866779,0.0001136181,0.000003633365,0.000008823815,0.0003911961],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4200665,"threshold_uncertainty_score":0.4045784,"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."}}