{"id":"W4414360531","doi":"10.24963/ijcai.2025/75","title":"Keypoints as Dynamic Centroids for Unified Human Pose and Segmentation","year":2025,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Centroid; Pose; Segmentation; Leverage (statistics); Cluster analysis; Embedding; Generalizability theory; 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":[0.00006944463,0.00005395867,0.00005388775,0.00009485021,0.0001604244,0.0001203403,0.00009312558,0.00002534047,0.00004741302],"category_scores_gemma":[0.000007347281,0.00005132789,0.00002181144,0.0000933984,0.00001225522,0.0002598239,0.00003864883,0.00002910699,0.00002831334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002539763,"about_ca_system_score_gemma":0.00001791171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001360321,"about_ca_topic_score_gemma":0.00002578112,"domain_scores_codex":[0.9995648,0.00001545122,0.0001012,0.0001713894,0.00005310481,0.00009410033],"domain_scores_gemma":[0.9997704,0.00002990831,0.00002619786,0.0001037902,0.00004297236,0.00002674605],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000210753,0.0001518162,0.0002966714,0.0000803422,0.00005541083,0.00000286985,0.0005042133,0.000006942737,0.08567275,0.6538928,0.006549406,0.2527657],"study_design_scores_gemma":[0.006248489,0.0006053364,0.02422421,0.0001297797,0.00006968323,0.00002136683,0.0007747014,0.1058732,0.1646844,0.6837273,0.01294374,0.0006977694],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3038509,0.00002022768,0.6749877,0.00133009,0.0003022475,0.0003542655,0.000002670794,0.0001598674,0.01899207],"genre_scores_gemma":[0.9779641,0.00001030589,0.00989404,0.001144542,0.00001668692,0.00002318845,0.00002431552,0.000002924591,0.01091992],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6741132,"threshold_uncertainty_score":0.2093091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009022249350812693,"score_gpt":0.3001523729574904,"score_spread":0.2911301236066777,"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."}}