{"id":"W2884328351","doi":"10.1109/tip.2018.2855438","title":"Information Fusion for Human Action Recognition via Biset/Multiset Globality Locality Preserving Canonical Correlation Analysis","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Multiset; Globality; Locality; Canonical correlation; Subspace topology; Pattern recognition (psychology); Computer science; Artificial intelligence; Feature (linguistics); Mathematics; Discrete 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0005743681,0.0002392325,0.0002503299,0.0005786257,0.001544944,0.0006353681,0.0002944139,0.0001902904,0.0001475045],"category_scores_gemma":[0.00002692637,0.0002537912,0.0002305501,0.001378413,0.0001099006,0.005486134,0.000006818138,0.0002700667,0.0001298212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002761039,"about_ca_system_score_gemma":0.0001069875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002589481,"about_ca_topic_score_gemma":0.0004897488,"domain_scores_codex":[0.9980221,0.0001403654,0.000642108,0.0004291727,0.0004252875,0.0003409516],"domain_scores_gemma":[0.9980881,0.00008199588,0.0003939737,0.0003779979,0.0009244261,0.0001335521],"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":[0.0001411827,0.0003212469,0.0000457612,0.0001745893,0.0001249039,6.250972e-7,0.0008625059,0.001287734,0.009489928,0.00002659296,0.0001881365,0.9873368],"study_design_scores_gemma":[0.001113343,0.000295958,0.001973708,0.0001182557,0.0004488309,0.00001260305,0.0001485847,0.9066011,0.0841362,0.004053955,0.0006066257,0.0004908416],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04082566,0.00000509299,0.9569238,0.0001979145,0.000485174,0.0004943263,0.00007935669,0.0004176749,0.0005709782],"genre_scores_gemma":[0.9700822,0.000006255722,0.02909217,0.0002732491,0.0001474201,0.000123965,0.0002028901,0.00001271942,0.00005918762],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.986846,"threshold_uncertainty_score":0.9999914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04239438905203577,"score_gpt":0.3254742274309975,"score_spread":0.2830798383789617,"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."}}