{"id":"W4393176994","doi":"10.1016/j.engappai.2024.108243","title":"A hybrid attention-guided ConvNeXt-GRU network for action recognition","year":2024,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Pooling; Artificial intelligence; Attention network; Pattern recognition (psychology); Kernel (algebra); Pyramid (geometry); Machine 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000449717,0.001436173,0.001411875,0.0008215166,0.0005636734,0.0007249594,0.00338959,0.0016335,0.007066625],"category_scores_gemma":[0.000717434,0.0006923599,0.0007494911,0.0009503202,0.0004294108,0.0009682172,0.001297962,0.001238561,0.00281877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009968133,"about_ca_system_score_gemma":0.001525371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03323158,"about_ca_topic_score_gemma":0.05302166,"domain_scores_codex":[0.9996639,0.00002582882,0.00001215733,0.0001412365,0.00007102956,0.00008584018],"domain_scores_gemma":[0.9997643,0.00004964181,0.00001634526,0.000041878,0.00008829545,0.00003952886],"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":[0.0003954926,0.0003449056,0.001021619,0.0001293824,0.0001412666,0.0001936793,0.00004433073,0.07455326,0.03338487,0.002446001,0.0190786,0.8682666],"study_design_scores_gemma":[0.00002434075,0.0001171412,0.0006213188,0.00001679953,0.00004253742,0.00008104866,0.00001401573,0.984197,0.01029044,0.001883228,0.002690458,0.00002168333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05795906,0.003715886,0.9103267,0.0007040019,0.0009806,0.0002251609,0.001144056,0.01496905,0.009975482],"genre_scores_gemma":[0.6258448,0.001129543,0.3360821,0.001336747,0.000317522,0.000265892,0.002679512,0.0005970693,0.03174675],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03323158,"threshold_uncertainty_score":0.06607634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06706709234277874,"score_gpt":0.3106290295556418,"score_spread":0.2435619372128631,"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."}}