{"id":"W2072536676","doi":"10.1109/tcsvt.2011.2177182","title":"Incremental Learning in Human Action Recognition Based on Snippets","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor; CARE Canada; University of Waterloo; General Electric (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Histogram; Pyramid (geometry); Representation (politics); Machine learning; Action (physics); Action recognition; Computer vision; Pattern recognition (psychology); Image (mathematics); 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":[],"consensus_categories":[],"category_scores_codex":[0.0003071486,0.0001684206,0.0002101604,0.001107091,0.0003947736,0.00006414097,0.0001714603,0.0002103371,0.00002550871],"category_scores_gemma":[0.000008394023,0.0001756752,0.00006421904,0.0003875493,0.00005068474,0.0003318925,0.000001695672,0.0003586673,0.000030342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001013739,"about_ca_system_score_gemma":0.00002613536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001061488,"about_ca_topic_score_gemma":0.00009971871,"domain_scores_codex":[0.9987232,0.00008445823,0.0003346101,0.0004486983,0.0001440016,0.0002650414],"domain_scores_gemma":[0.999446,0.00007151357,0.0001349951,0.0002225964,0.00007272619,0.00005211614],"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":[0.00009291115,0.001116859,0.0004088812,0.0002560611,0.00007644294,0.00003434606,0.0006671481,0.001085872,0.04674054,0.005673691,0.00009825145,0.943749],"study_design_scores_gemma":[0.01030617,0.009532948,0.002209822,0.001766303,0.0001312066,0.0003815293,0.002432808,0.2238261,0.7253403,0.01785503,0.004134068,0.002083707],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3060886,0.00001862535,0.6912822,0.00009664675,0.0006000766,0.0005763851,0.00001239673,0.0004577414,0.0008674024],"genre_scores_gemma":[0.9992021,0.00001792054,0.0002120739,0.0001003518,0.00002568451,0.0003530073,0.000005413188,0.00001673228,0.00006675357],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9416653,"threshold_uncertainty_score":0.7163826,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07588631854825996,"score_gpt":0.272050433681116,"score_spread":0.1961641151328561,"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."}}