{"id":"W4409366958","doi":"10.1609/aaai.v39i7.32792","title":"Stitch, Contrast, and Segment: Learning a Human Action Segmentation Model Using Trimmed Skeleton Videos","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Contrast (vision); Skeleton (computer programming); Segmentation; Artificial intelligence; Human skeleton; Computer vision; Computer science; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007766366,0.001605987,0.0009103132,0.001143947,0.0003254572,0.0006649956,0.001676934,0.001590091,0.002952117],"category_scores_gemma":[0.001953773,0.0006840175,0.001188982,0.0006058877,0.000860125,0.001327296,0.0008829865,0.002065104,0.001239461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001078845,"about_ca_system_score_gemma":0.00116085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009310316,"about_ca_topic_score_gemma":0.01527982,"domain_scores_codex":[0.9995311,0.00005415307,0.00001465396,0.0002843404,0.0000618975,0.00005393124],"domain_scores_gemma":[0.9994876,0.0001993676,0.00006023179,0.0001143092,0.00007377015,0.00006465842],"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":[0.0006170086,0.0003407214,0.003130625,0.0001837413,0.0001450915,0.0002357067,0.0001658526,0.2452132,0.03463836,0.004140972,0.00899087,0.7021978],"study_design_scores_gemma":[0.00001282187,0.000136557,0.0007135175,0.00001417465,0.00001420163,0.00007232028,0.00001674527,0.990684,0.005846027,0.001643071,0.000835311,0.00001133707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1060791,0.00098854,0.8799409,0.0003502328,0.0001695495,0.0003220888,0.0008530211,0.008397494,0.002899112],"genre_scores_gemma":[0.533982,0.0005801152,0.4495384,0.0005111996,0.0001135314,0.0003569471,0.004492986,0.0005177626,0.009907103],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009310316,"threshold_uncertainty_score":0.01851225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1113922087361536,"score_gpt":0.3464779246771,"score_spread":0.2350857159409463,"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."}}