Search

In the task of video salient object detection, how to effectively fuse spatiotemporal cues is the key to successfully detecting salient objects. Existing methods suffer from inadequate fusion as well as focusing too much on a single piece of information, which makes them perform poorly in complex scenes. To address these issues, we propose a new spatiotemporal full-stage interaction enhancement network (FIE-Net) for video salient object detection. FIE-Net applies spatiotemporal information interaction deeply to the encoder–decoder stage, fully exploring the complementarity of spatiotemporal modalities. Specifically, we introduce a progressive attention guidance unit in the encoder part, which can adaptively fuse spatiotemporal features under a progressive structure for efficient interaction of spatiotemporal information. In the decoder part, we incorporate a cross-modal global refinement unit, which utilizes spatiotemporal global features to refine and complement the encoder features to obtain more complete salient information. In addition, we employ a multilevel information correction unit to further filter the input features using spatial low-level features and optical flow prediction maps to obtain more accurate salient information. We conducted experiments on four dataset benchmarks. The experimental results show that our method is highly competitive with current state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

How to effectively fuse spatiotemporal clues is the key to improve the accuracy of video salient object detection. Although most existing methods have achieved great success regarding fusion strategies, the issue of reliability of spatiotemporal clues needs further investigation, and the use of unreliable spatiotemporal clues can corrupt the final saliency results. In this work, we propose a novel dynamic selection-fusion network (DSFNet) for video salient object detection, and DSFNet is jointly constructed by two branches. The one is the spatial learning network, which completes the learning of video sequences to obtain the spatial saliency of images. The other is the spatiotemporal contrast network, which creatively obtains the dynamic spatiotemporal saliency in the synchronized state by learning the video sequence and the corresponding optical flow images. To further screen and fuse the spatiotemporal clues, a series of joint modules for selection were developed, mainly including contrast transformation module (CTM), contrast analysis module (CAM) and selection guidance module (SGM) which play an important role in selecting spatiotemporal features. In addition, a fusion refinement module (FRM) is designed to further refine and enhance the input features. The experimental results show that the proposed method is significantly better than other algorithms in solving the problem of motion information distortion and spatiotemporal salient irrelevance. [ABSTRACT FROM AUTHOR]

Recently, deep learning has made impressive achievements in low-light image enhancement. Most existing deep learning-based methods use convolutional neural networks (CNN) by stacking network depth and modifying network architecture to improve feature extraction capabilities and restore degraded images. However, these methods have obvious defects. Although CNN excels at extracting local features, its small receptive field is unable to capture the global brightness, leading to overexposure. The Transformer model from natural language processing has recently produced positive outcomes in a variety of computer vision issues thanks to its excellent global modeling capabilities. However, its complex modeling method makes it difficult to capture local details and takes up many computing resources, making it challenging to apply to the enhancement of low-light images, especially high-resolution images. Based on deep convolution and Transformer characteristics, this paper proposes a Transformer-CNN Parallel Cooperative Network (TCPCNet), which supplements image details and local brightness while ensuring global brightness control. We also changed the calculation method of the traditional Transformer to be applied to enhance high-resolution low-light images without affecting performance. Extensive experiments on public datasets show that the proposed TCPCNet achieves comparable performance against the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

CO oxidative coupling to dimethyl oxalate (DMO) is an important approach for the product of ethylene glycol and CO elimination. In this work, the Co doped Pd/Al2O3 nanocatalyst was highly effective for CO oxidative coupling and enhanced remarkably CO conversion and the formation of DMO. The maximum DMO STY reached 1082 g L−1 h−1 over the Pd/Al2O3@1/20Co catalyst at 130 °C for 2 h under the space velocity of 3000 h−1, which is two times higher than that over the Pd/Al2O3 catalyst. The Co modification and its influence on the structure of the Pd/Al2O3 catalyst were also studied systematically by XRD, TEM, CO‐TPD, N2 physical adsorption and XPS techniques. An appropriate Co doing was confirmed to promote distinctly the generation of smaller Pd particles and the adjustment of the adsorption or activation of CO over the catalyst. A positive interaction between Pd nanoparticles and the modulated support with Co doping was demonstrated and favored the enhanced activity of the catalyst for the reaction. [ABSTRACT FROM AUTHOR]

Video-based pedestrian re-identification (ReID) is able to match the same pedestrian from various cameras in a complex real-world scene. The extracted representations can't contain all the useful information about the persons, due to the occlusion and misalignment of human areas between video sequences, and thus lack integrity and discrimination. To resolve this issue, we propose a new Spatial-Temporal Aware Network, which can mine and complement person features with feature relationships and intra-frame cues. According to the high correlation of the feature nodes of the same person between different video sequences, we employ the learned pedestrian feature nodes to construct the temporal relationship graph. In detail, the Temporal Interaction Module is designed to locate relevant pedestrian regions by modeling the correlation of feature nodes with reference nodes; and the Temporal Attention Module that we have designed is used to select more specific reference nodes. Then, we apply the designed Spatial Reference Module to adaptively mine each frame for fine-grained cues, making the spatial-temporal characteristics of persons more discriminative. We have implemented numerous experiments to demonstrate the excellent performance of STAN, such as achieving 88.0 % mAP and 89.5 % Rank-1 accuracy on the MARS dataset. [ABSTRACT FROM AUTHOR]

Catalytic conversion of glucose to lactic acid is a green promising strategy for the effective utilization of biomass‐derived carbohydrates to generate valuable chemicals. The generation of lactic acid would also be distinguishing in different reaction atmospheres. In this work, we firstly investigated the decomposition of lactic acid and glucose transformation to lactic acid in H2. No obvious decomposition of lactic acid was observed in H2. The activity testing results showed that glucose could be completely converted over the selected hydroxides, while the formation of lactic acid was closely related to the alkalinity of hydroxide. The yield of lactic acid was remarkably obtained to be 87 % over Ca(OH)2 at 220 °C for 3 h. Stronger alkalinity of the catalyst would facilitate glucose isomerization to fructose, and then easily be transformed into dihydroxyacetone or glyceraldehyde intermediates through reverse aldol condensation, which is beneficial to the generation of lactic acid. [ABSTRACT FROM AUTHOR]

Video anomaly detection is the study of detecting low probability anomalies from high probability normal behaviour. The imbalance of data raises the need to effectively distinguish between normal and abnormal behaviour in foreground targets. In the current state of research, the focus of many researchers has been on predictions closer to acquisition, but this need to effectively distinguish between normal and abnormal has received little attention. To address this problem, we propose a spatio-temporal enhancement network, a prediction-based unsupervised learning approach to video anomaly detection. In order to capture similar properties between foreground targets, we design the correlation enhancement module, which aims to quantify the spatial information of normal foreground targets. The temporal information enhancement module is also designed to stabilise the temporal information of normal foreground targets to reduce the effect of background variation and improve the robustness of the network structure. To clarify the boundary between normal and abnormal targets, a poorer substitution is represents the abnormal target feature vector, a superior substitution is represents the normal target feature vector. In this way, to obtain a clear and accurate locus of the abnormal occurrence time. We have extensively test on the UCSD Ped1, UCSD Ped2, and Avenue datasets and obtained desirable average AUC metrics of 82.7, 97.6, and 89.6, respectively. [ABSTRACT FROM AUTHOR]

Guided bone regeneration (GBR) is a frequently used technique for patients with insufficient alveolar bone. The discovery of bone substitutes that can enhance osteogenesis is critical for GBR. Graphdiyne (GDY), a newly discovered carbon‐based nanomaterial, has been recognized as the most stable allotrope of acetylene carbon and is anticipated to be able to promote osteogenesis. Whereas it still remains unknown whether it could enhance osteogenic differentiation of bone marrow mesenchymal stem cells (BMSCs). In this study, GDY was modified with polyethylene glycol (PEG) and the influences of GDY‐PEG at different concentrations on BMSCs cell growth and osteogenic differentiation were researched for the first time. In this study, we found that GDY‐PEG at low concentration possessed premium bio‐compatibility and revealed evident facilitation of BMSCs osteogenic differentiation. The cell growth and osteogenic differentiation of BMSCs treated with GDY‐PEG were dose‐dependent. GDY‐PEG at 1 μg/mL demonstrated the optimal promoting effects of BMSCs osteogenic differentiation. Moreover, the regulating effect of BMSCs osteogenic differentiation by GDY‐PEG might be associated with the Wnt/β‐catenin signaling pathway. In all, the present study indicated a novel application of GDY in promoting bone tissue regeneration, providing a novel biomaterial for bone augmentation in clinics. [ABSTRACT FROM AUTHOR]

Deep modal can provide supplementary features for RGB images, which deeply improves the performance of salient object detection (SOD). However, depth images are disturbed by external factors during the acquisition process, resulting in low-quality acquisitions. Moreover, there are differences between the RGB and depth modals, so simply fusing the two modals cannot fully complement the depth information into the RGB modal. To enhance the quality of the depth image and integrate the cross-modal information effectively, we propose a depth enhanced cross-modal cascaded network (DCCNet) for RGB-D SOD. The entire cascaded network includes a depth cascaded branch, a RGB cascaded branch and a cross-modal fusion strategy. In the depth cascaded branch, we design a depth preprocessing algorithm to enhance the quality of the depth image. And in the process of depth feature extraction, we adopt four cascaded cross-modal guided modules to guide the RGB feature extraction process. In the RGB cascaded branch, we design five cascaded residual adaptive selection modules to output the RGB image feature extraction in each stage. In the cross-modal fusion strategy, a cross-modal channel-wise refinement is adopted to fuse the top-level features of the different modal feature branches. Finally, the multiscale loss is adopted to optimize the network training. Experimental results on six common RGB-D SOD datasets show that the performance of the proposed DCCNet is comparable to that of the state-of-the-art RGB-D SOD methods. [ABSTRACT FROM AUTHOR]

Amino-functionalized monodisperse polymeric microspheres have great significance in water remediation. Herein, polypyrrole (PPy)-modified silica-coated magnetic monodispersed emulsion sphere (MES) microspheres (MES@Fe3O4@SiO2-PPy, MFSP) were successfully prepared via in situ polymerization for the adsorption of hexavalent chromium in an aqueous solution. The magnetism of MFSP enabled fast separation under an applied magnetic field. The results showed that MFSP exhibited outstanding adsorption for Cr(VI) (301.2 mg g−1 at pH 2.0), which followed the pseudo-second-order kinetic and Langmuir isotherm models. Moreover, the MFSP can be reused in the adsorption–desorption cycle by simple elution, and the removal rate of Cr(VI) by MFSP remained above 91% after five consecutive cycles. Combined with XPS, EDS, and Zeta potential measurement for adsorption mechanism analysis, it was concluded that the removal of Cr(VI) could be attributed to both adsorption and reduction. The combination of good adsorption performance and magnetic separation makes MFSP a promising candidate for the removal of low-concentration metal ions. [ABSTRACT FROM AUTHOR]

Nowadays the problem of image quality assessment (IQA) for screen content images (SCIs) has become a research hotspot as they are ubiquitous in multimedia applications. Although the quality assessment of natural images (NIs) has been continuously developed in the past few decades, few NI-oriented IQA methods can be directly applied on SCIs due to different visual characteristics between them. In this paper, we present a no-reference quality prediction approach considering the content information of SCIs, which is based on dual-channel multi-task convolutional neural network. First, we segment a SCI into small patches and classify them as the textual patches and the pictorial patches. Then, we devise a novel dual-channel convolutional neural network (CNN) to predict the quality of textual patches and pictorial patches. Finally, we propose an effective adaptive weighting strategy for quality score aggregation. The proposed CNN is built on an end-to-end multi-task learning framework, which assists the SCI quality prediction task through the histogram of oriented gradient (HOG) feature prediction task to learn a better mapping between the input patch and its quality score. The adaptive weighting strategy further improves the representation ability of each SCI patch. Experimental results on two largest SCI-oriented databases demonstrate that the proposed method outperforms most of the state-of-the-art no-reference IQA methods and the full-reference IQA methods. [ABSTRACT FROM AUTHOR]

Numerous screen content images (SCIs) have been produced to meet the needs of virtual desktop and remote display, which put forward a very urgent requirement for security and management of SCIs. Perceptual hashing is an effective way to deal with this issue. However, since SCIs are generally composed of pictures, graphics and texts, their intrinsic characteristics are different from those of natural images. Thus the previous hashing methods for natural images are not suitable for SCIs. In this article, we propose a perceptual hashing method for SCIs from the perspective of visual content understanding. Specifically, considering that the visual content understanding of SCIs mainly comes from textual regions, while the contours of text always have thinner width and higher contrast, it is decided to generate hash in the gradient field. An input screen image is first performed by some joint preprocessing operations. Then the maximum gradient magnitude and corresponding orientation information are extracted from three color channels R, G and B. Normalized histogram and local frequency coefficient features are further obtained from the maximum gradient magnitude. Finally, a hash sequence is constructed by statistics that are derived from extracted features. Experiments validated on three SCIs databases were conducted to evaluate classification between robustness and discrimination. Receiver operating characteristics (ROC) results demonstrate that the proposed method is superior to the state-of-the-art algorithms. Besides, SIQAD and SCID databases were leveraged to present the application in reduced-reference screen content image quality assessment, and comparisons show that our hashing could provide accurate predictions than other metrics. [ABSTRACT FROM AUTHOR]

Connected and Automated Vehicle (CAV) is a transformative technology that has great potential to improve urban traffic and driving safety. Electric Vehicle (EV) is becoming the key subject of next-generation CAVs by virtue of its advantages in energy saving. Due to the limited endurance and computing capacity of EVs, it is challenging to meet the surging demand for computing-intensive and delay-sensitive in-vehicle intelligent applications. Therefore, computation offloading has been employed to extend a single vehicle's computing capacity. Although various offloading strategies have been proposed to achieve good computing performace in the Vehicular Edge Computing (VEC) environment, it remains challenging to jointly optimize the offloading failure rate and the total energy consumption of the offloading process. To address this challenge, in this paper, we establish a computation offloading model based on Markov Decision Process (MDP), taking into consideration task dependencies, vehicle mobility, and different computing resources for task offloading. We then design a computation offloading strategy based on deep reinforcement learning, and leverage the Deep Q-Network based on Simulated Annealing (SA-DQN) algorithm to optimize the joint objectives. Experimental results show that the proposed strategy effectively reduces the offloading failure rate and the total energy consumption for application offloading. [ABSTRACT FROM AUTHOR]

Monodisperse polypyrrole/SBA-15 composite (PPy/SBA-15) was fabricated by in situ polymerization and used for Cr(VI) adsorption from aqueous solution. PPy/SBA-15 was characterized by numerous approaches. Factors affecting the Cr(VI) adsorption process, including the pH, the dose of adsorbent and contact time, were analyzed through batch experiments. The optimum experimental conditions were pH 2, dose of 4 g L−1 and contact time of 300 min. Meanwhile, PPy/SBA-15 had strong selective adsorption of Cr(VI) in co-existing ionic solution, the adsorption kinetics matched a pseudo-second-order kinetic model, and the adsorption isotherm data followed Langmuir adsorption isotherm models with a maximum adsorption capacity of 194.17 mg g−1 at 298 K, which is higher than that found in other reports of the same type of adsorbent. Regeneration evaluation demonstrated that the adsorbent can be recycled four times, retaining 92.58% of its removal rate. Moreover, EDX indicated that PPy/SBA-15 adsorbed Cr(VI) on its surface owing to ion exchange of chloride ions with either HCrO4− or Cr2O72−. XPS further certified that part of Cr(VI) was reduced to Cr(III). Overall, PPy/SBA-15 possesses capability as an alternative adsorbent to remove Cr(VI) from aqueous solution. [ABSTRACT FROM AUTHOR]

We propose a novel perceptual image hashing based on weighted discrete wavelet transform (DWT) statistical features. This hashing converts input image into a normalized image by bi-linear interpolation and color space conversion, extracts edge image of the normalized image via Canny operator, and divides the edge image into non-overlapping blocks. For each block, a three-level 2D DWT is applied to obtain different sub-bands and the weighted sum of the DWT statistics of these sub-bands is calculated. Finally, image hash is generated by concatenating and quantizing these weighted DWT features. Similarity of image hashes is measured by Euclidean distance. The Copydays dataset and the Uncompressed Color Image Database (UCID) are both used to evaluate classification between robustness and discrimination. Receiver operating characteristics curve comparisons illustrate that our hashing is superior to some state-of-the-art algorithms in classification performance with respect to robustness and discrimination. The LIVE Image Quality Assessment Database is used to validate our application in reduced-reference image quality assessment. Experimental results show that our hashing has better performance in image quality assessment than two popular measures, i.e. peak signal-to-noise ratio and structural similarity. [ABSTRACT FROM AUTHOR]

Selective encryption algorithms have emerged as a popular technique for protecting the privacy of images during real-time transmission. For selectively encrypted images, it is necessary to evaluate their security and usability with visual security indices, and there have been a series of studies in this area. However, those proposed visual security indices (VSI) are often ineffective. We present a multi-directional structure and content-aware features-based visual security index (MCVSI) to perform an objective assessment on selectively encrypted images. Considering that selectively encrypted images prevent the main contents from being easily identified, stable local features in the images are extracted to indicate the degree of image content leakage. Meanwhile, we extract spatial structure information that closely aligns with human visual perception to indicate the level of variation in the overall image skeleton. Next, these features are subjected to similarity measurements to produce two types of similarity, content perception feature similarity and structure feature similarity. Finally, our visual security index is built by connecting all feature similarities and their corresponding visual security scores using the regression module. The experimental results and analyses indicate that the proposed MCVSI outperforms many existing mainstream VSI in terms of higher performance and stronger robustness, particularly on low and medium quality images. [ABSTRACT FROM AUTHOR]

With the development of technology, it is becoming easier and easier for people to generate tampered images that are indistinguishable from the human eye, and the malicious use of these photos in news, academic papers, and criminal crimes has brought great harm to society. This paper proposes a deep convolutional neural network-based image forgery localization method to uncover the subtle differences between doctored images and real images. Specifically, the network achieves tampering localization through a three-stage enhancement scheme. First, the dilated convolution in the deep layer of the network is used to keep the feature map resolution constant, and the number of shallow convolutions is decreased to reduce the perceptual field, so the network focuses on local regions. Second, the feature enhancement module is used to fuse shallow features with deep features to effectively filter content information and highlight tampering features, making full use of local and global information to improve the generalization ability. Finally, the attention enhancement module reweights the convolutional feature maps in terms of channels and locations, respectively, to highlight the information regions around the forgery boundaries, thus guiding the network to capture more intrinsic features for image forgery. Extensive experimental results on several public datasets show that this method outperforms other state-of-the-art methods in image forgery localization. [ABSTRACT FROM AUTHOR]