{"id":"W4414598753","doi":"10.1016/j.knosys.2025.114549","title":"Dual attention focus network for few-shot skeleton-based action recognition","year":2025,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"National Mobile Communications Research Laboratory, Southeast University; Southeast University; National Natural Science Foundation of China","keywords":"Discriminative model; Focus (optics); Feature (linguistics); Similarity (geometry); Pattern recognition (psychology); Benchmark (surveying); Representation (politics); Weighting; Feature learning","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"],"consensus_categories":[],"category_scores_codex":[0.0008848261,0.0002874229,0.0003391358,0.00044678,0.0005756337,0.0004180417,0.0003079011,0.0002408539,0.00002715737],"category_scores_gemma":[0.00007612033,0.0002991733,0.0002803986,0.0008868725,0.00003930473,0.0004412159,0.00003328086,0.0001984578,0.0003720538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002946068,"about_ca_system_score_gemma":0.0003750319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005627864,"about_ca_topic_score_gemma":0.0001697017,"domain_scores_codex":[0.9976572,0.0003446024,0.000603563,0.0006652253,0.0002442015,0.0004851501],"domain_scores_gemma":[0.9979941,0.0004763337,0.0002865096,0.0004917003,0.0006376659,0.0001137305],"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":[0.0005978855,0.002043196,0.001736607,0.003668294,0.000418807,0.00002104347,0.0002576822,0.007692741,0.01552283,0.02269726,0.2127188,0.7326249],"study_design_scores_gemma":[0.00650965,0.0006415843,0.001898048,0.00227362,0.0002065916,0.00001178001,0.0001219128,0.8212876,0.02668966,0.007921462,0.1313065,0.001131579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01494467,0.0004525325,0.9691359,0.0005511362,0.006752507,0.001374982,0.00003534516,0.0006304828,0.006122435],"genre_scores_gemma":[0.9924052,0.000005143659,0.002879346,0.0002389532,0.001297488,0.0008885382,0.0003341086,0.00002890347,0.00192234],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9774605,"threshold_uncertainty_score":0.9999461,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05824830487641025,"score_gpt":0.3075772945777495,"score_spread":0.2493289897013393,"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."}}