{"id":"W4286750520","doi":"10.11159/mvml22.108","title":"LPYOLO: Low Precision YOLO for Face Detection on FPGA","year":2022,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Field-programmable gate array; Multithreading; Convolutional neural network; Embedded system; Edge device; Face detection; Deep learning; Object detection; Computer hardware; Facial recognition system; Artificial intelligence; Feature extraction; Pattern recognition (psychology); Operating system","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002176546,0.0008532171,0.0003146155,0.0006112424,0.0002248689,0.0006738391,0.001367721,0.0003491995,0.04460272],"category_scores_gemma":[0.0006082298,0.0003272874,0.0002423839,0.0003422995,0.0001626989,0.0006351858,0.0005003862,0.0005380207,0.008674309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005927998,"about_ca_system_score_gemma":0.0005383229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002969153,"about_ca_topic_score_gemma":0.004109726,"domain_scores_codex":[0.9997869,0.00001906238,0.00001317977,0.00005102302,0.00008501385,0.00004481662],"domain_scores_gemma":[0.9998705,0.0000260374,0.00001638465,0.00002639831,0.00004976512,0.00001081891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001923497,0.0001850919,0.003619904,0.001513115,0.000118266,0.0007060773,0.000365128,0.01469716,0.1102504,0.01554402,0.1939004,0.6571769],"study_design_scores_gemma":[0.0006139419,0.001249675,0.005067432,0.0004097383,0.000124473,0.001522265,0.0001652057,0.2400508,0.257564,0.004484073,0.4885728,0.0001756073],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08490096,0.005152134,0.6102182,0.0006453112,0.0007967215,0.0009426168,0.005895644,0.1634937,0.1279547],"genre_scores_gemma":[0.572034,0.001538345,0.2957559,0.00112101,0.0001190996,0.001095104,0.01007412,0.004262195,0.1140002],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04460272,"threshold_uncertainty_score":0.149211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01027742092619089,"score_gpt":0.2321835557627542,"score_spread":0.2219061348365633,"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."}}