We use two metrics for scene-level labeling comparison, i.e., total accuracy and average accuracy.
For object-level labeling comparison, the baseline methods include E-SVM and HV+GC, similar to that of [15].
For scene-level labeling comparison, the baseline is referred to that of Shotton et al. [4], which is the typical method in scene-level manner.
This was a randomized, open-label comparison of 3 regimens of AS monotherapy given as a single oral dose of 2, 4 or 6 mg/kg/day (AS2, AS4 and AS6) for 7 days (total doses 14, 28 and 42 mg/kg) in otherwise healthy adult patients with acute falciparum malaria.
Moreover, the study incorporated an open-label comparison with tiotropium 18 mcg once daily for 7 days.
We previously reported the first stage, a randomized open-label comparison of exenatide QW to exenatide BID in patients with type 2 diabetes over 30 weeks (17).
DURATION-1 and -5 were randomized control trials with open-label comparison of safety and efficacy profile of weekly versus 10 µg twice-daily exenatide use.
The study was a randomized, exploratory, active-controlled, open-label comparison of etravirine (n = 59) and a protease inhibitor chosen by the investigator (n = 57).
This 2-stage protocol consisted of a randomized, open-label comparison of exenatide QW and exenatide BID for 30 weeks, followed by an open-ended assessment period in which all patients received exenatide QW.
