Jin Xie

Learn More
Texture classification is a classical yet still active topic in computer vision and pattern recognition. Recently, several new texture classification approaches by modeling texture images as distributions over a set of textons have been proposed. These textons are learned as the cluster centers in the image patch feature space using the K-means clustering(More)
We demonstrate the first true real-time in vivo video imaging of extracellular protease expression using an ultrafast-acting and extended-use activatable probe. This simple, one-step technique is capable of boosting fluorescent signals upon target protease cleavage as early as 30 minutes from injection in a small animal model and is able to sustain the(More)
Opportunistic Routing (OR) has been proven effective for wireless mesh networks. However, the existing OR protocols cannot meet all the requirements for high-speed, multi-rate wireless mesh networks, including: running on commodity Wi-Fi interface, supporting TCP, low complexity, supporting multiple link layer data rates, and exploiting partial packets. In(More)
Complex geometric structural variations of 3D model usually pose great challenges in 3D shape matching and retrieval. In this paper, we propose a high-level shape feature learning scheme to extract features that are insensitive to deformations via a novel discriminative deep auto-encoder. First, a multiscale shape distribution is developed for use as input(More)
MRI is one of the most important imaging tools in clinics. It interrogates nuclei of atoms in a living subject, providing detailed delineation with high spatial and temporal resolutions. To compensate the innate low sensitivity, MRI contrast probes were developed and widely used. These are typically paramagnetic or superparamagnetic materials, functioning(More)
Shape descriptor is a concise yet informative representation that provides a 3D object with an identification as a member of some category. We have developed a concise deep shape descriptor to address challenging issues from ever-growing 3D datasets in areas as diverse as engineering , medicine, and biology. Specifically, in this paper, we developed novel(More)