Yuting Zhang

Learn More
Object detection systems based on the deep convolutional neural network (CNN) have recently made ground-breaking advances on several object detection benchmarks. While the features learned by these high-capacity neural networks are discriminative for categorization, inaccurate localization is still a major source of error for detection. Building upon(More)
Current computing systems depend on adaptation mechanisms to ensure that they remain in quiescent operating regions. These regions are often defined using efficiency, fairness, and stability properties. To that end, traditional research works in scalable server architectures and protocols have focused on promoting these properties by proposing even more(More)
Many latent factors of variation interact to generate sensory data; for example, pose, morphology and expression in face images. In this work, we propose to learn manifold coordinates for the relevant factors of variation and to model their joint interaction. Many existing feature learning algorithms focus on a single task and extract features that are(More)
With the increased use of "Virtual Machines" (VMs) as vehicles that isolate applications running on the same host, it is necessary to devise techniques that enable multiple VMs to share underlying resources both fairly and efficiently. To that end, one common approach is to deploy complex resource management techniques in the hosting infrastructure.(More)
This paper describes an algorithm for scheduling packets in real-time multimedia data streams. Common to these classes of data streams are service constraints in terms of bandwidth and delay. However, it is typical for real-time multimedia streams to tolerate bounded delay variations and, in some cases, finite losses of packets. We have therefore developed(More)
In addition to identifying the content within a single image, relating images and generating related images are critical tasks for image understanding. Recently, deep convolutional networks have yielded breakthroughs in predicting image labels, annotations and captions, but have only just begun to be used for generating high-quality images. In this paper we(More)
In most operating systems, the handling of interrupts is typically performed within the address space of the kernel. Moreover, interrupt handlers are invoked asynchronously during the execution of arbitrary processes. Unfortunately, this allows for a process’s time quantum to be consumed by arbitrary interrupt handling. To avoid significant impact to(More)
Aeromonas veronii strain B565 was isolated from aquaculture pond sediment in China. We present here the complete genome sequence of B565 and compare it with 2 published genome sequences of pathogenic strains in the Aeromonas genus. The result represents an independent stepwise acquisition of virulence factors of pathogenic strains in this genus.
Sea cucumber extracts have been widely used to treat individuals with inflammatory conditions in East Asia. The present study has been designed to test potential colon cancer-preventive properties of Frondanol A5, a glycolipid extract from the sea cucumber, Cucumaria frondosa, using in vivo and in vitro models of colon cancer. Chemopreventive efficacy of(More)
BACKGROUND Little is known about how Medicare Part D affects the medication refill adherence for cardiovascular and diabetes medications, particularly among beneficiaries without prior drug coverage. OBJECTIVES To evaluate Medicare Part D's effect on medication adherence among beneficiaries with hyperlipidemia, hypertension, and/or diabetes enrolled in(More)