{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004783428,0.0002323915,0.0001918432,0.0002590366,0.0005180888,0.0005472608,0.0001666474,0.0000963345,0.00002625903],"category_scores_gemma":[0.00005670279,0.0002468462,0.0001247936,0.0003610787,0.00001795329,0.000516056,0.00003397015,0.0003246347,0.0001449835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000133191,"about_ca_system_score_gemma":0.0001084469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002464133,"about_ca_topic_score_gemma":0.0000014591,"domain_scores_codex":[0.998242,0.000097916,0.000362431,0.0006897305,0.0002824437,0.0003255167],"domain_scores_gemma":[0.9989373,0.0005288959,0.0001506379,0.0001626241,0.0001470599,0.00007345215],"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":[0.0002193879,0.0002255773,0.00001594291,0.0004539666,0.00008285876,0.00000549237,0.0006762188,0.007929779,0.0799522,0.002712459,0.0002156016,0.9075105],"study_design_scores_gemma":[0.0008052001,0.0003117601,0.0001523736,0.0002636623,0.00003189872,0.000003980746,0.00006598145,0.9168884,0.07729152,0.003374824,0.0005091598,0.0003012813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1254069,0.000008497806,0.8697057,0.000163651,0.0005552594,0.001399018,0.000003657402,0.00146871,0.001288582],"genre_scores_gemma":[0.9812022,0.000003507959,0.017422,0.0003434408,0.0003805135,0.0002962735,0.0002888998,0.00003448766,0.00002863471],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9089586,"threshold_uncertainty_score":0.9999984,"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."}}