{"id":"W4312938499","doi":"10.1109/icpr56361.2022.9956539","title":"Classification-based Multi-task Learning for Efficient Pose Estimation Network","year":2022,"lang":"en","type":"article","venue":"2022 26th International Conference on Pattern Recognition (ICPR)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Tellabs (Canada)","funders":"","keywords":"Computer science; Inference; Artificial intelligence; Offset (computer science); Pose; Machine learning; Task (project management); Feature (linguistics); Multi-task learning; Feature extraction; Pattern recognition (psychology); Data mining","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006721541,0.0002602284,0.0002027249,0.0003974618,0.000904217,0.0003627089,0.0007512972,0.00007404054,0.003242444],"category_scores_gemma":[0.0001192772,0.0003000509,0.0001806576,0.0003412834,0.00003835997,0.0002954052,0.0001609093,0.0005164929,0.0004087791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003128719,"about_ca_system_score_gemma":0.0001725672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001860351,"about_ca_topic_score_gemma":0.00001124958,"domain_scores_codex":[0.9972497,0.0002959757,0.0005441343,0.0007472908,0.0007979398,0.0003649801],"domain_scores_gemma":[0.9982753,0.0002639293,0.0004973185,0.000298671,0.0005478837,0.0001169042],"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":[0.0002178066,0.001330078,0.001227956,0.00005421944,0.0001384061,0.00002073109,0.0005682046,0.2146431,0.001958631,0.01090176,0.005910025,0.7630291],"study_design_scores_gemma":[0.001369492,0.0003206061,0.00227827,0.00006239316,0.00001738065,0.00001136721,0.0001693149,0.9876509,0.0004959651,0.003000765,0.004256611,0.0003669757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02146381,0.00001201666,0.9688358,0.003155125,0.002681049,0.0007315828,0.0002388458,0.000344334,0.00253749],"genre_scores_gemma":[0.9861405,0.000009397937,0.00660746,0.002452327,0.0002955542,0.00120927,0.002613642,0.00003068856,0.000641096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9646767,"threshold_uncertainty_score":0.9999452,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09310461038073815,"score_gpt":0.3110063859402579,"score_spread":0.2179017755595197,"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."}}