{"id":"W2967130730","doi":"10.1007/978-3-030-27202-9_32","title":"Safely Caching HOG Pyramid Feature Levels, to Speed up Facial Landmark Detection","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Alcohol Countermeasure Systems (Canada); Toronto Metropolitan University","funders":"","keywords":"Computer science; Landmark; Artificial intelligence; Histogram; Pyramid (geometry); Feature (linguistics); Computer vision; Pattern recognition (psychology); Scale (ratio); Object detection; Naive Bayes classifier; Histogram of oriented gradients; Object (grammar); Image (mathematics); Support vector machine; 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":[0.002027002,0.00071771,0.0007867064,0.00105998,0.0003984149,0.000944957,0.003323093,0.000563231,0.00001402655],"category_scores_gemma":[0.0002624708,0.0006559962,0.0002177403,0.0009590184,0.0002397487,0.0007114343,0.001306187,0.001512445,0.000174273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004234285,"about_ca_system_score_gemma":0.0006155451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007139019,"about_ca_topic_score_gemma":0.0004755456,"domain_scores_codex":[0.9951078,0.0001202345,0.000491928,0.002085074,0.001248213,0.0009466988],"domain_scores_gemma":[0.9968945,0.0005948108,0.0002999927,0.001671516,0.000276978,0.0002621706],"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":[0.0000193622,0.00001142747,0.0002179887,0.00003927328,0.00001629956,0.00005772039,0.0007917418,0.03591352,0.001874853,0.001244212,0.00003016088,0.9597834],"study_design_scores_gemma":[0.00287697,0.001823059,0.03065963,0.002443539,0.00006258558,0.0008071311,0.000001742616,0.7047941,0.03970112,0.1412557,0.0681249,0.007449457],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007661522,0.0001960472,0.9858472,0.001144129,0.008639162,0.0005781793,0.00001536966,0.0002811166,0.002532681],"genre_scores_gemma":[0.6369551,0.0000210017,0.3555197,0.003325317,0.001633847,0.000005406806,0.000008194946,0.00008406333,0.002447353],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.952334,"threshold_uncertainty_score":0.9995891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0295659120196541,"score_gpt":0.282781595580986,"score_spread":0.2532156835613319,"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."}}