{"id":"W2033160484","doi":"10.1109/cimsivp.2014.7013267","title":"Improving codebook generation for action recognition using a mixture of Asymmetric Gaussians","year":2014,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Codebook; Computer science; Artificial intelligence; Bag-of-words model in computer vision; Histogram; Pattern recognition (psychology); Cluster analysis; Visual Word; Centroid; Set (abstract data type); Mixture model; Feature (linguistics); Context (archaeology); Bag-of-words model; Image retrieval; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001818881,0.0009065343,0.001513255,0.0013025,0.0004991985,0.0008419312,0.002286307,0.001054596,0.003038518],"category_scores_gemma":[0.007540548,0.0005771079,0.001063196,0.001390332,0.0006403197,0.001575445,0.001415336,0.001624238,0.002414404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008296272,"about_ca_system_score_gemma":0.001497153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01010947,"about_ca_topic_score_gemma":0.009785432,"domain_scores_codex":[0.9983291,0.0003277633,0.0001225177,0.0003752262,0.0006882605,0.0001572708],"domain_scores_gemma":[0.9971916,0.001000523,0.0001225416,0.0004417562,0.001086615,0.0001569574],"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":[0.0005247401,0.0002722971,0.001723919,0.0002027514,0.00009303115,0.0001472724,0.000225652,0.1250279,0.05133516,0.0109259,0.007422454,0.8020989],"study_design_scores_gemma":[0.00003488096,0.00007244666,0.0004060405,0.00001049961,0.00001815997,0.0001284825,0.00002841165,0.9828901,0.01204195,0.002309175,0.002037284,0.00002253876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005856005,0.0001761463,0.9925939,0.00005332647,0.00006009475,0.00004980106,0.0000498279,0.0008537029,0.0003071684],"genre_scores_gemma":[0.1574318,0.0002964653,0.8382663,0.000185889,0.0000729055,0.0001884003,0.0008175255,0.0002995169,0.002441153],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01010947,"threshold_uncertainty_score":0.02010125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08055488444783421,"score_gpt":0.2872355130592603,"score_spread":0.2066806286114261,"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."}}