Learn More
We present a method for detecting objects in images using a single deep neural network. Our approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location. At prediction time, the network generates scores for the presence of each object category in each default(More)
Recently, learning based hashing techniques have attracted broad research interests because they can support efficient storage and retrieval for high-dimensional data such as images, videos, documents, etc. However, a major difficulty of learning to hash lies in handling the discrete constraints imposed on the pursued hash codes, which typically makes hash(More)
Cancer-associated IDH mutations are characterized by neomorphic enzyme activity and resultant 2-hydroxyglutarate (2HG) production. Mutational and epigenetic profiling of a large acute myeloid leukemia (AML) patient cohort revealed that IDH1/2-mutant AMLs display global DNA hypermethylation and a specific hypermethylation signature. Furthermore, expression(More)
A number of human cancers harbor somatic point mutations in the genes encoding isocitrate dehydrogenases 1 and 2 (IDH1 and IDH2). These mutations alter residues in the enzyme active sites and confer a gain-of-function in cancer cells, resulting in the accumulation and secretion of the oncometabolite (R)-2-hydroxyglutarate (2HG). We developed a small(More)
The capacity to fix nitrogen is widely distributed in phyla of Bacteria and Archaea but has long been considered to be absent from the Pseudomonas genus. We report here the complete genome sequencing of nitrogen-fixing root-associated Pseudomonas stutzeri A1501. The genome consists of a single circular chromosome with 4,567,418 bp. Comparative genomics(More)
Deep Web contents are accessed by queries submitted to Web databases and the returned data records are enwrapped in dynamically generated Web pages (they will be called deep Web pages in this paper). Extracting structured data from deep Web pages is a challenging problem due to the underlying intricate structures of such pages. Until now, a large number of(More)
Manifold Ranking (MR), a graph-based ranking algorithm, has been widely applied in information retrieval and shown to have excellent performance and feasibility on a variety of data types. Particularly, it has been successfully applied to content-based image retrieval, because of its outstanding ability to discover underlying geometrical structure of the(More)
The main contribution of this paper is an approach for introducing additional context into state-of-the-art general object detection. To achieve this we first combine a state-of-the-art classifier (Residual-101 [14]) with a fast detection framework (SSD [18]). We then augment SSD+Residual-101 with deconvolution layers to introduce additional large-scale(More)
Studying program behavior is a central component in architectural designs. In this paper, we study and exploit one aspect of program behavior, the behavior repetition, to expedite simulation. Detailed architectural simulation can be long and computationally expensive. Various alternatives are commonly used to simulate a much smaller instruction stream to(More)