{"id":"W4224308757","doi":"10.1109/cvprw56347.2022.00403","title":"FenceNet: Fine-grained Footwork Recognition in Fencing","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Canada Research Chairs","keywords":"Fencing; Computer science; Artificial intelligence; Pattern recognition (psychology); Convolutional neural network; Wearable computer","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009373371,0.0005374853,0.0005268962,0.0008657456,0.0008504459,0.0006485305,0.0007340881,0.000184915,0.002202609],"category_scores_gemma":[0.00002477304,0.00057193,0.000186283,0.001212273,0.00007018829,0.0008226426,0.0004921997,0.001171543,0.0003747638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001887114,"about_ca_system_score_gemma":0.0001042438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006683637,"about_ca_topic_score_gemma":0.0002072238,"domain_scores_codex":[0.9954228,0.0007894194,0.0008570139,0.001375468,0.0008529178,0.000702413],"domain_scores_gemma":[0.9981444,0.0003906153,0.0004010203,0.0005651393,0.0002170943,0.0002817381],"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":[0.00008685164,0.0003544443,0.0003363945,0.00003488783,0.0000244632,0.0001215893,0.001027951,0.0002068925,0.0003682468,0.0001126784,0.00384287,0.9934827],"study_design_scores_gemma":[0.01014141,0.004979742,0.01896354,0.002937869,0.00009598285,0.0007659007,0.001438146,0.89071,0.003091947,0.05346028,0.008751268,0.004663904],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6001256,0.0001109964,0.3877332,0.003267442,0.004580657,0.00111538,0.0001423591,0.0005821562,0.002342236],"genre_scores_gemma":[0.9908934,0.0002433881,0.003274411,0.004088122,0.0004530267,0.0003156065,0.0004571425,0.00004579837,0.0002290541],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9888188,"threshold_uncertainty_score":0.9996732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04727545566979018,"score_gpt":0.266704969427767,"score_spread":0.2194295137579768,"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."}}