Shanghai University

About: Shanghai University is a education organization based out in Shanghai, Shanghai, China. It is known for research contribution in the topics: Microstructure & Graphene. The organization has 59583 authors who have published 56840 publications receiving 753549 citations. The organization is also known as: Shànghǎi Dàxué.

Hierarchical Alternate Interaction Network for RGB-D Salient Object Detection

Abstract: Existing RGB-D Salient Object Detection (SOD) methods take advantage of depth cues to improve the detection accuracy, while pay insufficient attention to the quality of depth information. In practice, a depth map is often with uneven quality and sometimes suffers from distractors, due to various factors in the acquisition procedure. In this article, to mitigate distractors in depth maps and highlight salient objects in RGB images, we propose a Hierarchical Alternate Interactions Network (HAINet) for RGB-D SOD. Specifically, HAINet consists of three key stages: feature encoding, cross-modal alternate interaction, and saliency reasoning. The main innovation in HAINet is the Hierarchical Alternate Interaction Module (HAIM), which plays a key role in the second stage for cross-modal feature interaction. HAIM first uses RGB features to filter distractors in depth features, and then the purified depth features are exploited to enhance RGB features in turn. The alternate RGB-depth-RGB interaction proceeds in a hierarchical manner, which progressively integrates local and global contexts within a single feature scale. In addition, we adopt a hybrid loss function to facilitate the training of HAINet. Extensive experiments on seven datasets demonstrate that our HAINet not only achieves competitive performance as compared with 19 relevant state-of-the-art methods, but also reaches a real-time processing speed of 43 fps on a single NVIDIA Titan X GPU. The code and results of our method are available at https://github.com/MathLee/HAINet .

Semantic Link Network-Based Model for Organizing Multimedia Big Data

Abstract: Recent research shows that multimedia resources in the wild are growing at a staggering rate. The rapid increase number of multimedia resources has brought an urgent need to develop intelligent methods to organize and process them. In this paper, the semantic link network model is used for organizing multimedia resources. A whole model for generating the association relation between multimedia resources using semantic link network model is proposed. The definitions, modules, and mechanisms of the semantic link network are used in the proposed method. The integration between the semantic link network and multimedia resources provides a new prospect for organizing them with their semantics. The tags and the surrounding texts of multimedia resources are used to measure their semantic association. The hierarchical semantic of multimedia resources is defined by their annotated tags and surrounding texts. The semantics of tags and surrounding texts are different in the proposed framework. The modules of semantic link network model are implemented to measure association relations. A real data set including 100 thousand images with social tags from Flickr is used in our experiments. Two evaluation methods, including clustering and retrieval, are performed, which shows the proposed method can measure the semantic relatedness between Flickr images accurately and robustly.

Fragile Watermarking With Error-Free Restoration Capability

Abstract: This paper proposes a novel fragile watermarking scheme capable of perfectly recovering the original image from its tampered version. In the scheme, a tailor-made watermark consisting of reference-bits and check-bits is embedded into the host image using a lossless data hiding method. On the receiver side, by comparing the extracted and calculated check-bits, one can identify the tampered image-blocks. Then, the reliable reference-bits extracted from other blocks are used to exactly reconstruct the original image. Although content replacement may destroy a portion of the embedded watermark data, as long as the tampered area is not too extensive, the original image information can be restored without any error.

Simultaneous Enhancement of Charge Separation and Hole Transportation in a TiO2–SrTiO3 Core–Shell Nanowire Photoelectrochemical System

Abstract: Efficient charge separation and transportation are key factors that determine the photoelectrochemical (PEC) water-splitting efficiency Here, a simultaneous enhancement of charge separation and hole transportation on the basis of ferroelectric polarization in TiO2 -SrTiO3 core-shell nanowires (NWs) is reported The SrTiO3 shell with controllable thicknesses generates a considerable spontaneous polarization, which effectively tunes the electrical band bending of TiO2 Combined with its intrinsically high charge mobility, the ferroelectric SrTiO3 thin shell significantly improves the charge-separation efficiency (ηseparation ) with minimized influence on the hole-migration property of TiO2 photoelectrodes, leading to a drastically increased photocurrent density ( Jph ) Specifically, the 10 nm-thick SrTiO3 shell yields the highest Jph and ηseparation of 143 mA cm-2 and 877% at 123 V versus reversible hydrogen electrode, respectively, corresponding to 83% and 79% improvements compared with those of pristine TiO2 NWs The PEC performance can be further manipulated by thermal treatment, and the control of SrTiO3 film thicknesses and electric poling directions This work suggests a material with combined ferroelectric and semiconducting features could be a promising solution for advancing PEC systems by concurrently promoting the charge-separation and hole-transportation properties