TADC: A Topic-Aware Dynamic Convolutional Neural Network for Aspect Extraction.

Aspect extraction is one of the key tasks in fine-grained sentiment analysis. This task aims to identify explicit opinion targets from user-generated documents. Currently, the mainstream methods for aspect extraction are built on recurrent neural networks (RNNs), which are difficult to parallelize. To accelerate the training/testing process, convolutional neural network (CNN)-based methods are introduced. However, such models usually utilize the same set of filters to convolve all input documents, and hence, the unique information inherent in each document may not be fully captured. To alleviate this issue, we propose a CNN-based model that employs a set of dynamic filters. Specifically, the proposed model extracts the aspects in a document using the filters generated from the aspect information intrinsic in the document. With the dynamically generated filters, our model is capable of learning more important features concerning aspects, thus promoting the effectiveness of aspect extraction. Furthermore, considering that aspects can be grouped into certain topics that conversely indicate the target words that need to be extracted, we naturally introduce a neural topic model (NTM) and integrate latent topics into the CNN-based module to help identify aspects. Experiments on two benchmark datasets demonstrate that the joint model is able to effectively identify aspects and produce interpretable topics.

Deep Listwise Triplet Hashing for Fine-Grained Image Retrieval.

Hashing is a practical approach for the approximate nearest neighbor search. Deep hashing methods, which train deep networks to generate compact and similarity-preserving binary codes for entities (e.g. images), have received lots of attention in the information retrieval community. A representative stream of deep hashing methods is triplet-based hashing that learns hashing models from triplets of data. The existing triplet-based hashing methods only consider triplets that are in the form of (q,q+,q-) , where q and q+ are in the same class and q and q- are in different classes. However, the number of possible triplets is approximately the cube of training examples, triplets used in the existing methods are only a small fraction of all possible triplets. This motivates us to develop a new triplet-based hashing method that adopts many more triplets in training phase. We propose Deep Listwise Triplet Hashing (DLTH) that introduces more triplets into batch-based training and a novel listwise triplet loss to capture the relative similarity in new triplets. This method has a pipeline of two steps. In Step 1, we propose a novel way to generate triplets from the soft class labels obtained by knowledge distillation module, where the triplets in the form of (q,q+,q-) are a subset of the newly obtained triplets. In Step 2, we develop a novel listwise triplet loss to train the hashing network, which seeks to capture the relative similarity between images in triplets according to soft labels. We conduct comprehensive image retrieval experiments on four benchmark datasets. The experimental results show that the proposed method has superior performances over state-of-the-art baselines.

Predicting the Incident Cases of Emerging Infectious Disease Using a Bayesian Probability Model - China, February 2020.

WHAT IS ALREADY KNOWN ABOUT THIS TOPIC?: The exact number of incident cases of emerging infectious diseases on a daily basis is of great importance to the disease control and prevention, but it is not directly available from the current surveillance system in time. WHAT IS ADDED BY THIS REPORT?: In this study, a Bayesian statistical method was proposed to estimate the posterior parameters of the gamma probability distribution of the lag time between the onset date and the reporting time based on the surveillance data. And then the posterior parameters and corresponding cumulative gamma probability distribution were used to predict the actual number of new incident cases and the number of unreported cases per day. The proposed method was used for predicting COVID-19 incident cases from February 5 to February 26, 2020. The final results show that Bayesian probability model predictions based on data reported by February 28, 2020 are very close to those actually reported a month later. WHAT ARE THE IMPLICATIONS FOR PUBLIC HEALTH PRACTICE?: This research provides a Bayesian statistical approach for early estimation of the actual number of cases of incidence based on surveillance data, which is of great value in the prevention and control practice of epidemics.

Clothing Landmark Detection Using Deep Networks With Prior of Key Point Associations.

This paper considers a problem of landmark point detection in clothes, which is important and valuable for clothing industry. A novel method for landmark localization has been proposed, which is based on a deep end-to-end architecture using prior of key point associations. With the estimated landmark points as input, a deep network has been proposed to predict clothing categories and attributes. A systematic design of the proposed detecting system is implemented by using deep learning techniques and a large-scale clothes dataset containing 145 000 upper-body clothing images with landmark annotations. Experimental results indicate that clothing categories and attributes can be well classified by using the detected landmark points, which are associated with regions of interest in clothes (e.g., the sleeves and the collars) and share robust learning representation property with respect to large variances of human poses, nonfrontal views, or occlusion. A comprehensive performance evaluation over two newly released datasets is carried out in this paper, showing that the proposed system with deep architecture for clothing landmark detection outperforms the state-of-the-art techniques.

Object-Location-Aware Hashing for Multi-Label Image Retrieval via Automatic Mask Learning.

Learning-based hashing is a leading approach of approximate nearest neighbor search for large-scale image retrieval. In this paper, we develop a deep supervised hashing method for multi-label image retrieval, in which we propose to learn a binary "mask" map that can identify the approximate locations of objects in an image, so that we use this binary "mask" map to obtain length-limited hash codes which mainly focus on an image's objects but ignore the background. The proposed deep architecture consists of four parts: 1) a convolutional sub-network to generate effective image features; 2) a binary "mask" sub-network to identify image objects' approximate locations; 3) a weighted average pooling operation based on the binary "mask" to obtain feature representations and hash codes that pay most attention to foreground objects but ignore the background; and 4) the combination of a triplet ranking loss designed to preserve relative similarities among images and a cross entropy loss defined on image labels. We conduct comprehensive evaluations on four multi-label image data sets. The results indicate that the proposed hashing method achieves superior performance gains over the state-of-the-art supervised or unsupervised hashing baselines.

Simultaneous detection and characterization of toxigenic Clostridium difficile directly from clinical stool specimens.

We employed a multiplex polymerase chain reaction (PCR) coupled with capillary electrophoresis (mPCR-CE) targeting six Clostridium difficile genes, including tpi, tcdA, tcdB, cdtA, cdtB, and a deletion in tcdC for simultaneous detection and characterization of toxigenic C. difficile directly from fecal specimens. The mPCR-CE had a limit of detection of 10 colony-forming units per reaction with no cross-reactions with other related bacterial genes. Clinical validation was performed on 354 consecutively collected stool specimens from patients with suspected C. difficile infection and 45 isolates. The results were compared with a reference standard combined with BD MAX Cdiff, real-time cell analysis assay (RTCA), and mPCR-CE. The toxigenic C. difficile species were detected in 36 isolates and 45 stool specimens by the mPCR-CE, which provided a positive rate of 20.3% (81/399). The mPCR-CE had a specificity of 97.2% and a sensitivity of 96.0%, which was higher than RTCA (x2 = 5.67, P = 0.017) but lower than BD MAX Cdiff (P = 0.245). Among the 45 strains, 44 (97.8%) were determined as nonribotype 027 by the mPCR-CE, which was fully agreed with PCR ribotyping. Even though ribotypes 017 (n = 8, 17.8%), 001 (n = 6, 13.3%), and 012 (n = 7, 15.6%) were predominant in this region, ribotype 027 was an important genotype monitored routinely. The mPCR-CE provided an alternative diagnosis tool for the simultaneous detection of toxigenic C. difficile in stool and potentially differentiated between RT027 and non-RT027.

Personalized Age Progression with Bi-Level Aging Dictionary Learning.

Age progression is defined as aesthetically re-rendering the aging face at any future age for an individual face. In this work, we aim to automatically render aging faces in a personalized way. Basically, for each age group, we learn an aging dictionary to reveal its aging characteristics (e.g., wrinkles), where the dictionary bases corresponding to the same index yet from two neighboring aging dictionaries form a particular aging pattern cross these two age groups, and a linear combination of all these patterns expresses a particular personalized aging process. Moreover, two factors are taken into consideration in the dictionary learning process. First, beyond the aging dictionaries, each person may have extra personalized facial characteristics, e.g., mole, which are invariant in the aging process. Second, it is challenging or even impossible to collect faces of all age groups for a particular person, yet much easier and more practical to get face pairs from neighboring age groups. To this end, we propose a novel Bi-level Dictionary Learning based Personalized Age Progression (BDL-PAP) method. Here, bi-level dictionary learning is formulated to learn the aging dictionaries based on face pairs from neighboring age groups. Extensive experiments well demonstrate the advantages of the proposed BDL-PAP over other state-of-the-arts in term of personalized age progression, as well as the performance gain for cross-age face verification by synthesizing aging faces.

Instance-Aware Hashing for Multi-Label Image Retrieval.

Similarity-preserving hashing is a commonly used method for nearest neighbor search in large-scale image retrieval. For image retrieval, deep-network-based hashing methods are appealing, since they can simultaneously learn effective image representations and compact hash codes. This paper focuses on deep-network-based hashing for multi-label images, each of which may contain objects of multiple categories. In most existing hashing methods, each image is represented by one piece of hash code, which is referred to as semantic hashing. This setting may be suboptimal for multi-label image retrieval. To solve this problem, we propose a deep architecture that learns instance-aware image representations for multi-label image data, which are organized in multiple groups, with each group containing the features for one category. The instance-aware representations not only bring advantages to semantic hashing but also can be used in category-aware hashing, in which an image is represented by multiple pieces of hash codes and each piece of code corresponds to a category. Extensive evaluations conducted on several benchmark data sets demonstrate that for both the semantic hashing and the category-aware hashing, the proposed method shows substantial improvement over the state-of-the-art supervised and unsupervised hashing methods.

FSMRank: feature selection algorithm for learning to rank.

In recent years, there has been growing interest in learning to rank. The introduction of feature selection into different learning problems has been proven effective. These facts motivate us to investigate the problem of feature selection for learning to rank. We propose a joint convex optimization formulation which minimizes ranking errors while simultaneously conducting feature selection. This optimization formulation provides a flexible framework in which we can easily incorporate various importance measures and similarity measures of the features. To solve this optimization problem, we use the Nesterov's approach to derive an accelerated gradient algorithm with a fast convergence rate O(1/T(2)). We further develop a generalization bound for the proposed optimization problem using the Rademacher complexities. Extensive experimental evaluations are conducted on the public LETOR benchmark datasets. The results demonstrate that the proposed method shows: 1) significant ranking performance gain compared to several feature selection baselines for ranking, and 2) very competitive performance compared to several state-of-the-art learning-to-rank algorithms.

Core antigen tests for hepatitis C virus: a meta-analysis.

Diagnosis and monitoring of hepatitis C virus (HCV) infection relies mainly on the detection of HCV antibodies and HCV RNA. HCV antibody test has a longer window period and is not applicable in the immunosuppressed population. Although HCV RNA test reduces the window period, it is still not widely recommended because of its high cost and requirement of specific equipment. HCV core antigen is another direct virological marker which has been investigated in recent years. HCV core antigen assay is as simple as the HCV antibodies assay and can detect HCV infection only 1 day delay compared to the HCV RNA assay. In order to evaluate the application of HCV core antigen test in HCV diagnosis and management, we performed this meta-analysis. Twenty five articles were finally included in meta-analysis. All statistical analyses were performed with MetaDisc 1.4 and Stata 11.0. The pooled sensitivity of HCV core antigen assay was 0.84 (95 % CI, 0.83-0.85), and the pooled specificity was 0.98 (95 % CI, 0.97-0.98). HCV core antigen assays may not displace HCV RNA assays to be a definitive diagnosis of HCV infection until now. Considering the higher sensitivity (0.926) and specificity (0.991) of subgroup, HCV-cAg detection is a promising method as a confirmatory test for HCV antibody positive, therapy-naive individuals. Explored by meta-regression and subgroup analysis, possible sources of heterogeneity of specificity was found, while the heterogeneity of sensitivity was still significant.