{"id":"W4236097319","doi":"10.32920/ryerson.14656041","title":"Safely caching HOG pyramid feature levels, to speed up facial landmark detection","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Pyramid (geometry); Landmark; Overhead (engineering); Feature (linguistics); Histogram of oriented gradients; Histogram; Cache; Set (abstract data type); Artificial intelligence; Encoding (memory); Frame (networking); Bayesian network; Pattern recognition (psychology); Data set; Computer vision; Image (mathematics); Data mining; Computer network; Mathematics","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":[0.0002943492,0.0003163239,0.0004207982,0.0003314647,0.0001929682,0.001024802,0.0007701198,0.0003537775,0.0002334261],"category_scores_gemma":[0.000100943,0.0002946955,0.0003526589,0.0005613415,0.00001457713,0.0002257474,0.001285602,0.0008073579,0.000198162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00014021,"about_ca_system_score_gemma":0.0001640863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005173815,"about_ca_topic_score_gemma":0.001567496,"domain_scores_codex":[0.9978992,0.0001372564,0.0002633327,0.0009227693,0.0004483432,0.0003290481],"domain_scores_gemma":[0.9987445,0.00003914012,0.0001178747,0.0006704613,0.0002106152,0.0002174428],"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":[0.00002426269,0.0001236604,0.0002847533,0.0001832386,0.0004775928,0.0001144765,0.002718948,0.01333052,0.02631351,0.0004130097,0.003432005,0.952584],"study_design_scores_gemma":[0.002440413,0.0002489731,0.02882449,0.001173789,0.0005089941,0.0002080695,0.002140007,0.6894001,0.2049646,0.003846068,0.06012197,0.006122502],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04886196,0.00007689801,0.9388133,0.004045209,0.002483429,0.0002382683,0.00002841426,0.0004199797,0.005032556],"genre_scores_gemma":[0.9663916,0.00003160882,0.02164666,0.001326741,0.0003197047,0.00001178255,0.00006725374,0.00001917619,0.01018544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9464615,"threshold_uncertainty_score":0.9999505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03104042598846666,"score_gpt":0.268314657159052,"score_spread":0.2372742311705854,"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."}}