Learn More
Supervised hashing aims to map the original features to compact binary codes that are able to preserve label based similarity in the Hamming space. Non-linear hash functions have demonstrated their advantage over linear ones due to their powerful generalization capability. In the literature, kernel functions are typically used to achieve non-linearity in(More)
Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neu-ral networks (CNNs) for the task. We show how to improve semantic segmentation through the use of contextual information. Specifically, we explore 'patch-patch' context and 'patch-background' context with deep CNNs. For learning the patch-patch(More)
Fast nearest neighbor searching is becoming an increasingly important tool in solving many large-scale problems. Recently a number of approaches to learning data-dependent hash functions have been developed. In this work, we propose a column generation based method for learning data-dependent hash functions on the basis of proximity comparison information.(More)
Most existing approaches to hashing apply a single form of hash function, and an optimization process which is typically deeply coupled to this specific form. This tight coupling restricts the flexibility of the method to respond to the data, and can result in complex optimization problems that are difficult to solve. Here we propose a flexible yet simple(More)
We consider the problem of depth estimation from a single molecular image in this work. It is a challenging task as no reliable depth cues are available, e.g., stereo correspondences , motions etc. Previous efforts have been focusing on exploiting geometric priors or additional sources of information , with all using hand-crafted features. Recently, there(More)
To study the biologic role of migration inhibitory factor (MIF), a pleiotropic cytokine, we generated a mouse strain lacking MIF by gene targeting in embryonic stem cells. Analysis of the role of MIF during sepsis showed that MIF-/- mice were resistant to the lethal effects of high dose bacterial lipopolysaccharide (LPS), or Staphylococcus aureus(More)
In this article, we tackle the problem of depth estimation from single monocular images. Compared with depth estimation using multiple images such as stereo depth perception, depth from monocular images is much more challenging. Prior work typically focuses on exploiting geometric priors or additional sources of information, most using hand-crafted(More)
Deep structured output learning shows great promise in tasks like semantic image segmenta-tion. We proffer a new, efficient deep structured model learning scheme, in which we show how deep Convolutional Neural Networks (CNNs) can be used to estimate the messages in message passing inference for structured prediction with Conditional Random Fields (CRFs).(More)
Heme oxygenase-1 (HO-1) is a stress-inducible enzyme with diverse cytoprotective effects, and reported to have an important role in angiogenesis recently. Here we investigated whether HO-1 transduced by mesenchymal stem cells (MSCs) can induce angiogenic effects in infarcted myocardium. HO-1 was transfected into cultured MSCs using an adenoviral vector. 1 ×(More)
Boosting is a method for learning a single accurate predictor by linearly combining a set of less accurate weak learners. Recently, structured learning has found many applications in computer vision. Inspired by structured support vector machines (SSVM), here we propose a new boosting algorithm for structured output prediction, which we refer to as(More)