{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000598683,0.0008462915,0.000665355,0.0008126787,0.0004366263,0.001207361,0.001299421,0.0009670868,0.003757004],"category_scores_gemma":[0.001792905,0.0003371275,0.0007613022,0.0006289066,0.0004973965,0.001956227,0.00140239,0.001066514,0.001073128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008543045,"about_ca_system_score_gemma":0.0007559043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008653156,"about_ca_topic_score_gemma":0.01034775,"domain_scores_codex":[0.9995564,0.0000893682,0.00001981184,0.0001885628,0.00007988956,0.00006612417],"domain_scores_gemma":[0.9996374,0.0001244414,0.0000331432,0.0000922039,0.00008086921,0.00003194575],"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":[0.0005857727,0.0002159589,0.003669067,0.0003089824,0.0002073805,0.0003636313,0.0002155468,0.08767169,0.05647825,0.02335409,0.01816174,0.8087679],"study_design_scores_gemma":[0.0000245812,0.00008939957,0.002403834,0.00003435575,0.00008725088,0.0001806853,0.0000340739,0.9352928,0.01440725,0.0385167,0.00890609,0.00002309789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07486934,0.006570304,0.8986256,0.001252952,0.000777002,0.0001188216,0.0007733091,0.006154073,0.01085855],"genre_scores_gemma":[0.8801965,0.001679885,0.1068528,0.0006672922,0.0003945048,0.0001002447,0.001030176,0.0003074899,0.008771122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008653156,"threshold_uncertainty_score":0.0172056,"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."}}