{"id":"W1504587477","doi":"10.1007/978-3-540-88690-7_42","title":"Unsupervised Learning of Skeletons from Motion","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Motion (physics); Artificial intelligence; Feature (linguistics); Sequence (biology); Probabilistic logic; Algorithm; Structure from motion; Motion capture; Series (stratigraphy); Parsing; Computer vision; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002924612,0.0003772715,0.0004913489,0.000662585,0.0002369528,0.0001353842,0.002247628,0.0001855541,0.00003384683],"category_scores_gemma":[0.000123498,0.0003584567,0.0001393441,0.0005482691,0.0005566734,0.000704548,0.0009994506,0.0008446795,0.00003534634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001418391,"about_ca_system_score_gemma":0.000265779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004245954,"about_ca_topic_score_gemma":0.000008711468,"domain_scores_codex":[0.9970132,0.00003885798,0.0005019546,0.001169256,0.0008406244,0.0004360939],"domain_scores_gemma":[0.9979087,0.0004069822,0.0003117559,0.001008185,0.0002309352,0.0001334396],"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":[0.000002056997,0.00001641071,0.00007913722,0.000009238178,0.000004893875,0.00003254704,0.0006709115,0.03012692,0.000798098,0.001745958,0.00001054474,0.9665033],"study_design_scores_gemma":[0.0003066256,0.0001024237,0.0004296275,0.0003849385,0.00000438866,0.00002840678,2.351946e-7,0.9526128,0.004173496,0.03802685,0.003442775,0.0004873848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001751037,0.0006530204,0.9954497,0.0003207365,0.0008164475,0.0001662875,0.000003255021,0.0001484625,0.002266963],"genre_scores_gemma":[0.1482542,0.000244985,0.850362,0.0005955155,0.0002372974,0.000002458019,0.000009156732,0.00003144759,0.0002629928],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9660159,"threshold_uncertainty_score":0.9998868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01640670177287233,"score_gpt":0.2488933770068397,"score_spread":0.2324866752339674,"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."}}