T
Tingfa Xu
Researcher at Beijing Institute of Technology
Publications - 143
Citations - 3195
Tingfa Xu is an academic researcher from Beijing Institute of Technology. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 15, co-authored 104 publications receiving 2009 citations. Previous affiliations of Tingfa Xu include University of California, Merced & Chinese Ministry of Education.
Papers
More filters
Journal ArticleDOI
Scale-Aware Fast R-CNN for Pedestrian Detection
TL;DR: SAF R-CNN as discussed by the authors introduces multiple built-in subnetworks which detect pedestrians with scales from disjoint ranges, and outputs from all of the sub-networks are then adaptively combined to generate the final detection results that are shown to be robust to large variance in instance scales.
Posted Content
Perceptual Generative Adversarial Networks for Small Object Detection
TL;DR: This work addresses the small object detection problem by developing a single architecture that internally lifts representations of small objects to super-resolved ones, achieving similar characteristics as large objects and thus more discriminative for detection.
Proceedings ArticleDOI
Perceptual Generative Adversarial Networks for Small Object Detection
TL;DR: Li et al. as discussed by the authors proposed a new Generative Adversarial Network (GAN) model that improves small object detection through narrowing representation difference of small objects from the large ones.
Journal ArticleDOI
Attentive Contexts for Object Detection
TL;DR: Zhang et al. as discussed by the authors proposed an attention-to-context convolution neural network (AC-CNN) for object detection, which consists of one attention-based global contextualized subnetwork and one multi-scale local contextualized (MLC) subnetwork.
Proceedings ArticleDOI
Deep Semantic Face Deblurring
TL;DR: Zhang et al. as mentioned in this paper proposed to incorporate global semantic priors as input and impose local structure losses to regularize the output within a multi-scale deep CNN to restore sharp images with more facial details.