{"id":"W3173340069","doi":"10.1145/3447686","title":"Improving Action Recognition via Temporal and Complementary Learning","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Intelligent Systems and Technology","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; Vector Institute","funders":"Nvidia","keywords":"Computer science; Pooling; Representation (politics); Fuse (electrical); Artificial intelligence; Feature learning; Machine learning; Action recognition; Deep learning; Pattern recognition (psychology); Temporal database; Action (physics); Data mining; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007702509,0.001510286,0.001177623,0.001115424,0.0003159955,0.0008247332,0.001509158,0.001070296,0.002992795],"category_scores_gemma":[0.002038109,0.0003433719,0.001013617,0.001277979,0.0006388038,0.002476043,0.001265532,0.001383779,0.00175981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000723669,"about_ca_system_score_gemma":0.0009518167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006845803,"about_ca_topic_score_gemma":0.01010815,"domain_scores_codex":[0.9992021,0.00007848706,0.00003289015,0.0003625187,0.0002113479,0.0001127823],"domain_scores_gemma":[0.9994175,0.0001654988,0.00008474919,0.0001511397,0.0001259016,0.00005514035],"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":[0.0002856711,0.0002739897,0.001920681,0.0001379676,0.0001191077,0.00015625,0.00006244134,0.06456761,0.04275106,0.004346781,0.007156472,0.8782219],"study_design_scores_gemma":[0.00001107649,0.0001279003,0.001560345,0.00001664001,0.00005684066,0.0001681014,0.00003169364,0.9716465,0.01817405,0.005703702,0.002483654,0.00001955149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05442808,0.001777604,0.9336687,0.0003692322,0.0002727301,0.00007239188,0.0005861576,0.004258541,0.004566655],"genre_scores_gemma":[0.6694498,0.001478416,0.3165133,0.0006536298,0.0002541716,0.00009851334,0.002351277,0.0002725286,0.008928388],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006845803,"threshold_uncertainty_score":0.01361191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04123009817537312,"score_gpt":0.2678034478186185,"score_spread":0.2265733496432454,"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."}}