Standard sliding window based object detection requires dense classifier evaluation on densely sampled locations in scale space in order to achieve an accurate localization. To avoid such dense evaluation, selective search based algorithms only evaluate the classifier on a small subset of object proposals. Notwithstanding the demonstrated success, object proposals do not guarantee perfect overl...

• Dr. Kwang-Jin Koh for the opportunity to be a part of his research efforts; • Dr. Carl Dietrich, Dr. Leslie Pendleton, and Dr. Roofia Galeshi for the oversight and mentoring services provided throughout the duration of the program; • A special thanks to PhD student Hedieh Elyasi for her patience, as well as her abundant time and effort spent aiding in the learning/research process. • Why Samp...

Volumetric measures of the brain and ventricles were derived from CT films and related to intellectual variables from the Wechsler Adult Intelligence Scale (WAIS). Subjects were patients referred for neurological examination for headache or somatic complaints, sometimes accompanied by anxiety or dysphoric affect (N = 41), for whom a comprehensive neurological work-up revealed no evidence of abn...

BACKGROUND Network scale-up is an indirect method for estimating the size of hidden, hard-to-count or high risk populations. Social network size estimation is the first step in this method. The present study was conducted with the purpose of estimating the social network size of the Tehran Province residents and its determinants. METHODS Maximum Likelihood Estimation was applied to estimate p...

Methods based on convolutional neural network (CNN) have demonstrated tremendous improvements on single image super-resolution. However, the previous methods mainly restore images from one single area in the low resolution (LR) input, which limits the flexibility of models to infer various scales of details for high resolution (HR) output. Moreover, most of them train a specific model for each ...