Most real systems consist of a large number of interacting, multi-typed components, while most contemporary researches model them as homogeneous networks, without distinguishing different types of objects and links in the networks. Recently, more and more researchers begin to consider these interconnected, multi-typed data as heterogeneous information networks, and develop structural analysis approaches by leveraging the rich semantic meaning of structural types of objects and links in the networks. Compared to widely studied homogeneous network, the heterogeneous information network contains richer structure and semantic information, which provides plenty of opportunities as well as a lot of challenges for data mining. In this paper, we provide a survey of heterogeneous information network analysis. We will introduce basic concepts of heterogeneous information network analysis, examine its developments on different data mining tasks, discuss some advanced topics, and point out some future research directions. Index Termsheterogeneous information network, data mining, semi-structural data, meta path

In this paper, we propose an efficient algorithm to directly restore a clear image from a hazy input. The proposed algorithm hinges on an end-to-end trainable neural network that consists of an encoder and a decoder. The encoder is exploited to capture the context of the derived input images, while the decoder is employed to estimate the contribution of each input to the final dehazed result using the learned representations attributed to the encoder. The constructed network adopts a novel fusion-based strategy which derives three inputs from an original hazy image by applying White Balance (WB), Contrast Enhancing (CE), and Gamma Correction (GC). We compute pixel-wise confidence maps based on the appearance differences between these different inputs to blend the information of the derived inputs and preserve the regions with pleasant visibility. The final dehazed image is yielded by gating the important features of the derived inputs. To train the network, we introduce a multi-scale approach such that the halo artifacts can be avoided. Extensive experimental results on both synthetic and real-world images demonstrate that the proposed algorithm performs favorably against the state-of-the-art algorithms.

In this study, we investigated lipopolysaccharide (LPS)-induced cognitive impairment and neuroinflammation in C57BL/6J mice by using behavioral tests, immunofluorescence, enzyme-linked immunosorbent assay (ELISA) and Western blot. We found that LPS treatment leads to sickness behavior and cognitive impairment in mice as shown in the Morris water maze and passive avoidance test, and these effects were accompanied by microglia activation (labeled by ionized calcium binding adaptor molecule-1, IBA-1) and neuronal cell loss (labeled by microtubule-associated protein 2, MAP-2) in the hippocampus. The levels of interleukin-4 (IL-4) and interleukin-10 (IL-10) in the serum and brain homogenates were reduced by the LPS treatment, while the levels of tumor necrosis factor-α (TNF-α), interleukin-1β (IL-1β), prostaglandin E2 (PGE 2 ) and nitric oxide (NO) were increased. In addition, LPS promoted the expression of cyclooxygenase-2 (COX-2) and inducible nitric oxide synthase (iNOS) in the brain homogenates. The Western blot analysis showed that the nuclear factor kappa B (NF-κB) signaling pathway was activated in the LPS groups. Furthermore, VIPER, which is a TLR-4-specific inhibitory peptide, prevented the LPS-induced neuroinflammation and cognitive impairment. These data suggest that LPS induced cognitive impairment and neuroinflammation via microglia activation by activating the NF-kB signaling pathway; furthermore, we compared the time points, doses, methods and outcomes of LPS administration between intraperitoneal and intracerebroventricular injections of LPS in LPS-induced neuroinflammation and cognitive impairment, and these data may provide additional insight for researchers performing neuroinflammation research.

Discriminative correlation filters (DCFs) have been shown to perform superiorly in visual tracking. They only need a small set of training samples from the initial frame to generate an appearance model. However, existing DCFs learn the filters separately from feature extraction, and update these filters using a moving average operation with an empirical weight. These DCF trackers hardly benefit from the end-to-end training. In this paper, we propose the CREST algorithm to reformulate DCFs as a one-layer convolutional neural network. Our method integrates feature extraction, response map generation as well as model update into the neural networks for an end-to-end training. To reduce model degradation during online update, we apply residual learning to take appearance changes into account. Extensive experiments on the benchmark datasets demonstrate that our CREST tracker performs favorably against state-of-the-art trackers. 1