{"id":"W4404869848","doi":"10.1016/j.asoc.2024.112558","title":"Unsupervised prototype self-calibration based on hybrid attention contrastive learning for enhanced few-shot action recognition","year":2024,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Calibration; Shot (pellet); Action (physics); Artificial intelligence; Pattern recognition (psychology); Speech recognition; Physics","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":[0.0005869892,0.0007077688,0.001288939,0.0007687173,0.0003257931,0.0005937645,0.001803731,0.0009387343,0.002759879],"category_scores_gemma":[0.001308574,0.0004188124,0.0005701404,0.0006607109,0.0003675261,0.0008871014,0.001354056,0.001094455,0.001344117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003776412,"about_ca_system_score_gemma":0.0006530057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002637962,"about_ca_topic_score_gemma":0.005370573,"domain_scores_codex":[0.9994388,0.00005473589,0.00001941259,0.0002364414,0.000157744,0.00009286581],"domain_scores_gemma":[0.9993172,0.0001750023,0.00005139061,0.0001475878,0.0002596967,0.00004923027],"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":[0.0003254514,0.0002686396,0.001235548,0.0001093463,0.00008271728,0.00008565424,0.00008984125,0.02233041,0.130026,0.001147939,0.003067652,0.8412309],"study_design_scores_gemma":[0.00001192938,0.0001325938,0.002661943,0.00001309031,0.00003734089,0.0001860272,0.00002542723,0.9573358,0.03718062,0.001110567,0.001282479,0.00002212377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04997231,0.0004345687,0.9445103,0.00007610342,0.0001065662,0.0000763736,0.0001054583,0.002738871,0.001979384],"genre_scores_gemma":[0.6673474,0.0002930118,0.3251356,0.00029824,0.0000685901,0.0001340396,0.0005918798,0.0003390343,0.005792283],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002759879,"threshold_uncertainty_score":0.0092327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03389630046798382,"score_gpt":0.2745478046729182,"score_spread":0.2406515042049344,"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."}}