{"id":"W7126195995","doi":"10.18280/isi.301222","title":"Hybrid CNN-Transformer for Dynamic Indian Sign Language Recognition with Non-Manual Gesture Analysis","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Hand Gesture Recognition Systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Gesture; Gesture recognition; Sign language; Feature (linguistics); Sign (mathematics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001393799,0.0007055626,0.0009944403,0.002578894,0.0008840886,0.001762725,0.0007804792,0.0004315597,0.00006817689],"category_scores_gemma":[0.0002086147,0.0006471098,0.0005086639,0.00384528,0.0002440453,0.006836589,0.00007461155,0.000461334,0.0002532876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007237793,"about_ca_system_score_gemma":0.0006981994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002246835,"about_ca_topic_score_gemma":0.0003811737,"domain_scores_codex":[0.9957312,0.0002262625,0.001738889,0.0006441507,0.0007241437,0.0009353879],"domain_scores_gemma":[0.9962385,0.0003358871,0.0009804734,0.000776517,0.001420268,0.0002483934],"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":[0.0003267651,0.0001230845,0.0005900561,0.003098067,0.002502929,0.00002336218,0.04663024,0.001249669,0.000152601,0.0002364164,0.0007058324,0.944361],"study_design_scores_gemma":[0.02087582,0.004879221,0.05436888,0.01532029,0.01297261,0.0008476922,0.05621434,0.7607613,0.02955364,0.01306047,0.02254763,0.00859806],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1482645,0.0003168254,0.8400381,0.0003145817,0.0009108928,0.002567189,0.0006385078,0.0002299299,0.006719552],"genre_scores_gemma":[0.9886709,0.00008544731,0.007190387,0.0007523934,0.0001213337,0.0006665931,0.00198011,0.00002818538,0.0005045842],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9357629,"threshold_uncertainty_score":0.999598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007135161689478239,"score_gpt":0.2437039616720779,"score_spread":0.2365687999825996,"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."}}