{"id":"W2782082266","doi":"10.1109/ism.2017.30","title":"Heterogeneous Features Fusion with Collaborative Representation Learning for 3D Action Recognition","year":2017,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Representation (politics); Discriminative model; Computer science; Artificial intelligence; Action recognition; Feature (linguistics); Feature learning; Sequence (biology); Task (project management); Pattern recognition (psychology); Action (physics); Feature extraction; Feature vector; Machine learning; Class (philosophy)","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":[0.0001193759,0.0001037387,0.00009851175,0.00008313466,0.00118091,0.0006456472,0.000190551,0.00006240673,0.00004556281],"category_scores_gemma":[0.00008147665,0.00008569258,0.0000367895,0.00008256843,0.00002978157,0.001376877,0.00004587743,0.00009815891,0.00004438209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003214793,"about_ca_system_score_gemma":0.00003233883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004005968,"about_ca_topic_score_gemma":0.0001823847,"domain_scores_codex":[0.999189,0.00005464533,0.0001168806,0.0003309675,0.0001644649,0.0001440978],"domain_scores_gemma":[0.9990067,0.00006135876,0.0002516086,0.0002858431,0.0003475578,0.0000469215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001725159,0.00006068411,0.000257977,0.00001919123,0.00003793044,0.000007258628,0.0005565084,0.0002766301,0.005505502,0.000447943,0.001080502,0.9915774],"study_design_scores_gemma":[0.00664851,0.003384056,0.02708902,0.0003485047,0.0001343606,0.0002927158,0.001470195,0.1337841,0.7778606,0.01937805,0.02805618,0.001553725],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1852557,0.00001797906,0.8025017,0.0007850793,0.0004388757,0.000674842,0.000004731666,0.0003074753,0.01001357],"genre_scores_gemma":[0.9433033,0.00006163999,0.05392031,0.0001467244,0.000198836,0.0001229622,0.00007712137,0.00001213201,0.002156952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9900236,"threshold_uncertainty_score":0.9082723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05281045456844188,"score_gpt":0.3239450548318696,"score_spread":0.2711346002634277,"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."}}