Learn More
Approximate nearest neighbor search is an efficient strategy for large-scale image retrieval. Encouraged by the recent advances in convolutional neural networks (CNNs), we propose an effective deep learning framework to generate binary hash codes for fast image retrieval. Our idea is that when the data labels are available, binary codes can be learned by(More)
In this paper, we propose a new unsupervised deep learning approach called DeepBit to learn compact binary descriptor for efficient visual object matching. Unlike most existing binary descriptors which were designed with random projections or linear hash functions, we develop a deep neural network to learn binary descriptors in an unsupervised manner. We(More)
Household dust was collected from 82 residential homes within the Sydney metropolitan area. The geometric mean concentrations of metals in the household dust were Cd, 1.9 microg/g; Cr, 64.3 microg/g; Cu, 103 microg/g; Fe, 2740 microg/g; Mn, 54 microg/g; Ni, 15.6 microg/g; Pb, 85.2 microg/g; and Zn, 437 microg/g. Differences in household income level,(More)
This paper presents an effective approach for detecting abandoned luggage in surveillance videos. We combine short- and long-term background models to extract foreground objects, where each pixel in an input image is classified as a 2-bit code. Subsequently, we introduce a framework to identify static foreground regions based on the temporal transition of(More)
BACKGROUND Stereotactic radiosurgery has proven a safe and effective treatment of cranial nerve sheath tumors. A similar approach should be successful for histologically identical spinal nerve sheath tumors. METHODS The preliminary results of linear accelerator-based spinal radiosurgery were retrospectively reviewed for a group of 25 nerve sheath tumors.(More)
Mitochondrial oxidative phosphorylation is the major source of energy in cardiac muscle. In the streptozotocin-induced diabetic (STZ-DM) mice, myocardial oxidative phosphorylation was perturbated and oxidative phosphorylation complex V (ATP synthase) activity was significantly reduced. To determine the independent effects of hyperglycemia and insulin(More)
IMPORTANCE Immunomodulatory anticancer drugs, such as the anti-programmed death-1 drug pembrolizumab, have shown promising results in trials, and more patients will receive such treatments. Little is known about cutaneous adverse events (AEs) caused by these drugs and their possible correlation with treatment response. OBJECTIVE To describe the frequency(More)
This paper deals with the problem of clothing retrieval in a recommendation system. We develop a hierarchical deep search framework to tackle this problem. We use a pre-trained network model that has learned rich mid-level visual representations in module 1. Then, in module 2, we add a latent layer to the network and have neurons in this layer to learn(More)
Generative adversarial networks (GANs) have great successes on synthesizing data. However, the existing GANs restrict the discriminator to be a binary classifier, and thus limit their learning capacity for tasks that need to synthesize output with rich structures such as natural language descriptions. In this paper, we propose a novel generative adversarial(More)