{"id":"W2897585580","doi":"10.1109/tmm.2018.2875510","title":"Multimodal Learning for Human Action Recognition Via Bimodal/Multimodal Hybrid Centroid Canonical Correlation Analysis","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Canonical correlation; Centroid; Computer science; Modalities; Artificial intelligence; Pattern recognition (psychology); Discriminative model; Correlation; Feature vector; Feature (linguistics); Machine learning; 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":[0.0003979803,0.0003792042,0.0004040005,0.0009940712,0.001320538,0.0002131744,0.0003585987,0.0002409112,0.0004937216],"category_scores_gemma":[0.00003567676,0.0004118132,0.0005211792,0.0009571936,0.0001531191,0.001091912,0.000005069062,0.0006109275,0.0006494835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002867813,"about_ca_system_score_gemma":0.0000877313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003476105,"about_ca_topic_score_gemma":0.0006325907,"domain_scores_codex":[0.9971159,0.0002389521,0.0006357386,0.0009296541,0.0004945728,0.0005852549],"domain_scores_gemma":[0.9980261,0.0003879126,0.0003181592,0.0004626298,0.0005293799,0.0002758618],"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":[0.000302373,0.0009804412,0.0001988407,0.00003107332,0.0007456507,0.000007447991,0.0009309807,0.02369096,0.03570502,0.00002928511,0.0001954915,0.9371824],"study_design_scores_gemma":[0.001950946,0.00057789,0.001716841,0.0000264603,0.0004371124,0.00001491784,0.00004747983,0.8972968,0.09649116,0.0004540795,0.0005036887,0.0004825615],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.145674,0.00000461852,0.851225,0.0001356584,0.001567558,0.0006247825,0.00005726902,0.0005443633,0.0001667304],"genre_scores_gemma":[0.9634145,0.00001514629,0.03489106,0.0001495262,0.0005512575,0.000224236,0.0002809308,0.00004228113,0.0004310192],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9366999,"threshold_uncertainty_score":0.9999796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03197822218404654,"score_gpt":0.2916044915662906,"score_spread":0.259626269382244,"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."}}