BACKGROUND Interferon-γ release assays (IGRAs) for TB have the potential to replace the tuberculin skin test (TST) in screening for latent tuberculosis infection (LTBI). The higher per-test cost of IGRAs may be compensated for by lower post-screening costs (medical attention, chest x-rays and chemoprevention), given the higher specificity of the new tests as compared to that of the conventional...

In this paper we introduce an unsupervised method for mining and modeling latent search concepts. We use Latent Dirichlet Allocation (LDA), a generative probabilistic topic model, to exhibit highly-specific query-related topics from pseudo-relevant feedback documents. Our approach automatically estimates the number of latent concepts as well as the needed amount of feedback documents, without a...

Treatment of latent tuberculosis (TB) infection with 3 months of rifampicin/isoniazid is a major part of preventive TB programmes. The effectiveness of treatment of latent TB infection can only be assessed by rates of subsequent breakdown and there are few outcome data for this combination of rifampicin/isoniazid. Therefore, the aim of the present study was to estimate the failure rate followin...

A long-standing challenge in information retrieval is to disambiguate query words for more precise search results. However, two or more meanings of a word in a query, or polysemy, deteriorate the precision effectiveness of information retrieval systems. There is a need for correct and effective information retrieval in many information systems such as health care and customer relationship manag...

The user ratings in recommendation systems are usually in the form of ordinal discrete values. To give more accurate prediction of such rating data, maximum margin matrix factorization (MF) was proposed. Existing MF algorithms, however, either have massive computational cost or require expensive model selection procedures to determine the number of latent factors (i.e. the rank of the matrix to...

Latent SVMs (LSVMs) are a class of powerful tools that have been successfully applied to many applications in computer vision. However, a limitation of LSVMs is that they rely on linear models. For many computer vision tasks, linear models are suboptimal and nonlinear models learned with kernels typically perform much better. Therefore it is desirable to develop the kernel version of LSVM. In t...

A common approach for handling the complexity and inherent ambiguities of 3D human pose estimation is to use pose priors learned from training data. Existing approaches however, are either too simplistic (linear), too complex to learn, or can only learn latent spaces from “simple data”, i.e., single activities such as walking or running. In this paper, we present an efficient stochastic gradien...

In this paper, we propose a new approach for domain generalization by exploiting the low-rank structure from multiple latent source domains. Motivated by the recent work on exemplar-SVMs, we aim to train a set of exemplar classifiers with each classifier learnt by using only one positive training sample and all negative training samples. While positive samples may come from multiple latent doma...

Generative adversarial networks (GANs) are a powerful framework for generative tasks. However, they are difficult to train and tend to miss modes of the true data generation process. Although GANs can learn a rich representation of the covered modes of the data in their latent space, the framework misses an inverse mapping from data to this latent space. We propose Invariant Encoding Generative...

The standard recurrent neural network language model (rnnlm) generates sentences one word at a time and does not work from an explicit global sentence representation. In this work, we introduce and study an rnn-based variational autoencoder generative model that incorporates distributed latent representations of entire sentences. This factorization allows it to explicitly model holistic propert...