{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003160804,0.0001637123,0.0001834734,0.0002083289,0.0004602401,0.0003038714,0.0004107729,0.00007706344,0.0000171612],"category_scores_gemma":[0.0001189594,0.0001417749,0.00006303937,0.0003920123,0.0001134542,0.0006431264,0.000146089,0.000268903,0.000007341263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008186837,"about_ca_system_score_gemma":0.00007638918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003697647,"about_ca_topic_score_gemma":0.00000793596,"domain_scores_codex":[0.9987234,0.00002428961,0.00040524,0.0003752226,0.0002638366,0.0002079468],"domain_scores_gemma":[0.9991191,0.00004982347,0.0003129897,0.0001105177,0.0003602133,0.00004737136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003229271,0.00008473701,0.0001082391,0.00006031465,0.00002026656,1.487913e-7,0.0008749951,0.001132802,0.6496317,0.2317057,0.00003490661,0.1163139],"study_design_scores_gemma":[0.00005469601,0.00006264965,0.00005493261,0.0001663152,0.00001943971,0.000001316098,0.0004846798,0.3807271,0.5412081,0.07710141,0.000015569,0.0001038109],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6574338,0.00001297636,0.3377457,0.0008761547,0.0002108208,0.0003937697,0.000001465676,0.00008870635,0.003236565],"genre_scores_gemma":[0.9970527,0.0000306498,0.002287375,0.0001864365,0.00002989939,0.00002076934,0.000001008891,0.000006498325,0.000384689],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3795942,"threshold_uncertainty_score":0.5781412,"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."}}