{"id":"W3119138272","doi":"10.1109/icpr48806.2021.9412916","title":"Context Matters: Self-Attention for Sign Language Recognition","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Hand Gesture Recognition Systems","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sign language; Context (archaeology); Sign (mathematics); Benchmark (surveying); Language model; Aggregate (composite); Traffic sign; Modalities; Natural language processing; Artificial intelligence; Modality (human–computer interaction); Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005618947,0.0002870067,0.0004041834,0.0001786301,0.00008357476,0.0008405391,0.0005845918,0.0003432772,0.0001188086],"category_scores_gemma":[0.00004375052,0.000276477,0.0003203955,0.0001607499,0.00001183303,0.0003616035,0.0004671099,0.0002791703,0.0003191217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009774214,"about_ca_system_score_gemma":0.000148049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008484496,"about_ca_topic_score_gemma":0.00007637835,"domain_scores_codex":[0.9978588,0.0002153452,0.0004748508,0.0008536956,0.0003046357,0.0002927236],"domain_scores_gemma":[0.9982299,0.0001999583,0.0002878229,0.0006997722,0.0004753529,0.0001072156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002051167,0.0005518422,0.00008866301,0.002711642,0.0006860325,0.0001059569,0.0108803,0.00001449442,0.005423721,0.001244808,0.05162218,0.9266499],"study_design_scores_gemma":[0.03279096,0.002574336,0.007450482,0.02953006,0.00272149,0.002635338,0.08002422,0.2048102,0.2523841,0.07388555,0.2847843,0.02640892],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009423106,0.0003624615,0.9799135,0.003077094,0.002639796,0.001312516,0.00005921244,0.0007909291,0.002421379],"genre_scores_gemma":[0.7163128,0.00007723521,0.2691004,0.007204819,0.001179573,0.001615151,0.001651342,0.00007438694,0.002784345],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9002409,"threshold_uncertainty_score":0.9999688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03035558673371856,"score_gpt":0.2684708853713201,"score_spread":0.2381152986376016,"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."}}