{"id":"W2036502167","doi":"10.1109/iccv.2005.59","title":"Conditional models for contextual human motion recognition","year":2005,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":286,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Conditional random field; Discriminative model; Hidden Markov model; Computer science; Conditional independence; CRFS; Artificial intelligence; Maximum-entropy Markov model; Graphical model; Pattern recognition (psychology); Inference; Machine learning; Markov random field; Markov chain; Markov model; Variable-order Markov model; Image segmentation","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":[0.0001429055,0.00008426413,0.00007905912,0.0001009906,0.0002326651,0.0001097839,0.0001452664,0.00005395251,0.0003791071],"category_scores_gemma":[0.00000838379,0.00008427971,0.00007214556,0.00006816663,0.00001985078,0.001533301,0.00002144212,0.000055592,0.0003363946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000038611,"about_ca_system_score_gemma":0.0000150333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004736686,"about_ca_topic_score_gemma":0.00002075009,"domain_scores_codex":[0.9992584,0.00002193359,0.0001914145,0.0002390026,0.0001363372,0.0001529014],"domain_scores_gemma":[0.9995384,0.00004598407,0.0000616936,0.0001210001,0.0001765588,0.0000563366],"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":[0.000008116251,0.0002043885,0.000003393584,0.00000983668,0.00002028082,6.47179e-7,0.0001977931,0.0005920493,0.002699585,0.5301038,0.01643426,0.4497259],"study_design_scores_gemma":[0.001450312,0.0001493268,0.0001694415,0.00001433741,0.00001106721,0.00002151874,0.00004441595,0.3771288,0.02392014,0.5869023,0.009893837,0.0002944793],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01189717,0.000006376899,0.969116,0.000893341,0.00009653249,0.0002325015,0.00002528413,0.0002457018,0.0174871],"genre_scores_gemma":[0.9616101,0.000002209905,0.03502357,0.001382999,0.000348759,0.00008730911,0.0003297144,0.000006415989,0.001208939],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9497129,"threshold_uncertainty_score":0.4323784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07528731668020994,"score_gpt":0.2903697616629481,"score_spread":0.2150824449827382,"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."}}