Search

This study aims to enhance the high-temperature resistance of ultrahigh-performance concrete (UHPC) by optimizing the cement-fly ash-silica fume ternary cement matrix composition and the geometric characteristics of the plastic fibers. The UHPC was designed and prepared with the cement-fly ash-silica fume ternary cement matrix through simplex centroid method and 2% volume fraction steel fiber. Polypropylene fibers with different geometric characteristics were incorporated to enhance the high-temperature resistance. The fire resistance is examined through the high-temperature exposure test. The initial bursting temperature is recorded, and the deterioration of mechanical performance is characterized. It was found that the decrepitation temperature of UHPC first increases and then decreases with the fly ash (FA) content. Meanwhile, the influence of the silica fume (SF) and cement content on the decrepitation temperature is not obvious. The optimum mix ratio of 50%–65% cement, 20%–30% FA, and 10%–20% SF is recommended to prepared the cementitious matrix with 450°C or higher initial burst temperature. The crack mouth opening displacement (CMOD) test assisted with digital image correlation (DIC) examination is conducted to characterize the fracture performance before and after high-temperature exposure. It was found that the fracture resistance of UHPC first increases and then decreases with the silica fume content, which reaches the maximum value of 16.64 N/mm with 27% SF content. Meanwhile the high-temperature resistance of UHPC increases and then decreases with the increase of the length of the doped polypropylene (PP) fibers. The added 1.2% volume fraction PP fiber can resolve the spalling issues of the UHPC materials, and the residual compressive strengths after exposure to 1,000°C of UHPC samples containing 15 mm–18 μm and 15 mm–33 μm fibers can exceed 50 MPa. This study can serve as a solid base for the fire resistance design of UHPC materials in field construction. [ABSTRACT FROM AUTHOR]

Purpose: Current evidence regarding the use of commercially available immersive virtual reality (VR) headsets and compatible VR exercise apparatus in the promotion of individuals' physical activity (PA) is lacking. This exploratory study investigated the acute effects of a VirZoom VR exercise bike (vBike) on college students' physical responses compared to an exergaming bike (eBike) and a traditional stationary exercise bike (tBike). Method: Forty-eight college students (34 females, Xage = 23.58 ± 3.39; XBMI = 23.81 ± 3.57) completed three separate 20-minute cycling sessions on the vBike, eBike, and tBike in a counterbalanced order. Outcomes included rating of perceived exertion (RPE), assessed at 4-minute intervals throughout each cycling session, and overall PA, operationalized as pedal revolution counts (PRC) during each session. Results: Linear models indicated significant group differences between exercise modalities for RPE (F (2,138) = 14.76–27.30, all p <.001, η2 = 0.17–0.27) and PRC (F (2,138) = 74.862, p <.001, η2 = 0.48). Pairwise comparisons revealed that RPE was reported significantly higher at each time point (i.e., 4th minute, 8th minute, 12th minute, 16th minute, and 20th minute) during the tBike session vs. the vBike and eBike sessions (p <.001) and that participants had higher PRC during the vBike session vs. the eBike and tBike sessions (p <.001). Conclusion: A commercially available VR exercise bike would trigger greater overall PA as compared to exergaming and traditional cycling while being perceived less intense. Future intervention studies conducted in real-world settings to determine cause and effect relationship are warranted. [ABSTRACT FROM AUTHOR]

Generic multiple object tracking aims to recover the trajectories for generic moving objects of the same category. This task relies on the ability of effectively extracting representative features of the target objects. To this end, we propose a novel prototype learning based model, PLGMOT, that can explore the template features of an exemplar object and extend to more objects to acquire their prototype. Their prototype features can be continuously updated during the video, in favor of generalization to all the target objects with different appearances. More importantly, on the public benchmark GMOT-40, our method achieves more than 14% advantage over the state-of-the-art methods, with less than 0.5% of the training data that is not even completely annotated in the form of bounding boxes, thanks to our proposed point-to-box label refinement training algorithm and hierarchical motion-aware association algorithm. • A prototype learning based generic multi-object detector. • A point-to-box label refinement training algorithm. • A hierarchical motion-aware association algorithm for tracking. • Extensive experiments demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Ultra-high resolution image segmentation has raised increasing interests in recent years due to its realistic applications. In this paper, we innovate the widely used high-resolution image segmentation pipeline, in which an ultra-high resolution image is partitioned into regular patches for local segmentation and then the local results are merged into a high-resolution semantic mask. In particular, we introduce a novel locality-aware context fusion based segmentation model to process local patches, where the relevance between local patch and its various contexts are jointly and complementarily utilized to handle the semantic regions with large variations. Additionally, we present the alternating local enhancement module that restricts the negative impact of redundant information introduced from the contexts, and thus is endowed with the ability of fixing the locality-aware features to produce refined results. Furthermore, in comprehensive experiments, we demonstrate that our model outperforms other state-of-the-art methods in public benchmarks and verify the effectiveness of the proposed modules. Our released codes will be available at: https://github.com/liqiokkk/FCtL. [ABSTRACT FROM AUTHOR]

[Display omitted] • Exploring the correlation between spatially resolved spectra and corn seed vigor. • Acquisition of seed spectral information at 0.2 mm intervals. • Spectral ratio methods are used to improve the prediction accuracy of the model. • The endosperm side of the seed is more suitable for testing. Seed vigor is an essential quality evaluation index for seed selection. However, accurately detecting the vigor of a single corn seed is challenging. In this study, we constructed a single-fiber spatially resolved detection device using visible/near-infrared spectroscopy to investigate the patterns and correlations between spatially resolved spectroscopy (SRS) at 500–1000 nm and seed vigor. The device collected spectral data at a light source–detector distance of 5–6.6 mm on the embryo side (S1) and endosperm side (S2) of the corn seeds. The proposed spectral ratio method based on SRS and spectral combination analysis achieved an improvement in the detection accuracy of different corn seed vigor. Modeling by SG-CARS-PLSDA using the ratio method showed further improvement in the prediction ability. The highest accuracy for both S1 and S2 in the Zhengdan 958 variety was 91.67 %, while those of S1 and S2 for the Shaandan 650 variety were 86.67 % and 88.33 %, respectively. In addition, SRS was found to be more advantageous in S2 acquisition, verifying the potential of SRS in the non-destructive testing of seed vigor. This provides a favorable reference for the comprehensive evaluation of other internal quality indices of seeds. [ABSTRACT FROM AUTHOR]

Objective. This systematic review synthesized current randomized controlled trials (RCTs) examining casual evidence regarding the effects of traditional and exergaming-based physical activity (PA) interventions on motor skill development in typically developed children (i.e., those aged 6-12 years). Methods. We adhered to the PRISMA-P statement and searched electronic databases (Medline, PsycInfo, Web of Science, PubMed, ERIC, Scopus, and SportDiscus) from inception through July 2020. We screened for peer reviewed RCTs published in English between 2000 and 2020 examining the effect of PA on motor skill development in healthy children. Results. A total of 25 RCTs were included, 20 (80%) of which reported significant improvements in children's motor skill performance. Specifically, 18 studies examined traditional PA interventions and 7 studies examined exergaming-based PA interventions, 83% and 71% of which observed statistically significant improvements in children's motor skill development, respectively. Conclusions. Findings support the causal evidence regarding the effects of PA on motor skill development in children. Notable limitations of this review included heterogeneity of measurement protocols and assessment tools used to test children's motor skills across studies, a wide range of PA intervention dose across studies, and the lack of power analyses and long-term follow-up assessments in individual studies to discern appropriate sample sizes and long-term effectiveness, respectively. To further strengthen the evidence in this emerging field, we advocate for future RCTs to employ a priori power analyses, long-term follow-up measurements, and more exergaming-based interventions to allow for comparisons with traditional PA interventions, to explore the dose response and moderating relationships between PA and motor skill development in childhood, and to utilize homogenous assessment instruments to allow for more rigorous, quantitative syntheses. [ABSTRACT FROM AUTHOR]

Existing video salient object detection (VSOD) methods focus on exploring either short-term or long-term temporal information. However, temporal information is exploited in a global frame-level or regular grid structure, neglecting inter-frame structural dependencies. In this article, we propose to learn long-term structural dependencies with a structure-evolving graph convolutional network (GCN). Particularly, we construct a graph for the entire video using a fast supervoxel segmentation method, in which each node is connected according to spatio-temporal structural similarity. We infer the inter-frame structural dependencies of salient object using convolutional operations on the graph. To prune redundant connections in the graph and better adapt to the moving salient object, we present an adaptive graph pooling to evolve the structure of the graph by dynamically merging similar nodes, learning better hierarchical representations of the graph. Experiments on six public datasets show that our method outperforms all other state-of-the-art methods. Furthermore, We also demonstrate that our proposed adaptive graph pooling can effectively improve the supervoxel algorithm in the term of segmentation accuracy. [ABSTRACT FROM AUTHOR]

The tracking-by-detection framework receives growing attention through the integration with the convolutional neural networks (CNNs). Existing tracking-by-detection-based methods, however, fail to track objects with severe appearance variations. This is because the traditional convolutional operation is performed on fixed grids, and thus may not be able to find the correct response while the object is changing pose or under varying environmental conditions. In this paper, we propose a deformable convolution layer to enrich the target appearance representations in the tracking-by-detection framework. We aim to capture the target appearance variations via deformable convolution, which adaptively enhances its original features. In addition, we also propose a gated fusion scheme to control how the variations captured by the deformable convolution affect the original appearance. The enriched feature representation through deformable convolution facilitates the discrimination of the CNN classifier on the target object and background. The extensive experiments on the standard benchmarks show that the proposed tracker performs favorably against the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

At present, most methods of urban change detection with synthetic aperture radar (SAR) images are based on image amplitude information. SAR images of the same region over different periods are usually compared and analyzed by using the difference method, which often neglects the SAR image interference information, exhibiting sensitivity to changes in ground scatterers. Therefore, this study presented a novel method combining the difference method and the SAR coherence coefficient to accurately and comprehensively detect the characteristics of urban change information. In this method, the amplitude difference between two images was obtained by the image difference method, and the suspected change areas in the urban area were determined. The suspected change areas of the image were further analyzed by using the coherence coefficient of the images and were regarded as genuinely changed areas when the results of the difference method and the coherence coefficient both changed. Finally, the proposed method and the difference method were employed to conduct a comparative study at Huilongguan Village in Changping District of Beijing city, China. Results indicate that the difference method can only reflect urban changes caused by urban construction (e.g., demolition and urban expansion), whereas the proposed method can not only detect urban changes due to urban construction but also remove urban pseudo-changes attributed to season change, vegetation, and tree growth. Thus, the proposed method can effectively improve the accuracy of change detection. Comparative analysis and field verification of the selected region of interest showed that the result accuracy of the proposed method reaches 84.5%, which is much higher than that of the single difference method (61.4%). This finding proves that the proposed method is feasible for urban change detection, and the conclusions can also provide a reference for urban planning and construction. [ABSTRACT FROM AUTHOR]

In this paper, we present an approach that utilizes multiple exemplar agent-based motion models (AMMs) to extract motion features (representing crowd behaviors) from the captured crowd trajectories. In the exemplar-based framework, we propose an iterative optimization algorithm to measure the correlation between any exemplar AMM and the trajectory data. It is based on the Extended Kalman Smoother and KL-divergence. In addition, based on the proposed correlation measure, we introduce the novel individual feature, in combination with the holistic feature, to describe crowd motions. Our results show that the proposed features perform well in classifying real-world crowd scenes. [ABSTRACT FROM AUTHOR]

Synthesizing novel views from a single view image is a highly ill-posed problem. We discover an effective solution to reduce the learning ambiguity by expanding the single-view view synthesis problem to a multi-view setting. Specifically, we leverage the reliable and explicit stereo prior to generate a pseudo-stereo viewpoint, which serves as an auxiliary input to construct the 3D space. In this way, the challenging novel view synthesis process is decoupled into two simpler problems of stereo synthesis and 3D reconstruction. In order to synthesize a structurally correct and detail-preserved stereo image, we propose a self-rectified stereo synthesis to amend erroneous regions in an identify-rectify manner. Hard-to-train and incorrect warping samples are first discovered by two strategies, (1) pruning the network to reveal low-confident predictions; and (2) bidirectionally matching between stereo images to allow the discovery of improper mapping. These regions are then inpainted to form the final pseudo-stereo. With the aid of this extra input, a preferable 3D reconstruction can be easily obtained, and our method can work with arbitrary 3D representations. Extensive experiments show that our method outperforms state-of-the-art single-view view synthesis methods and stereo synthesis methods. [ABSTRACT FROM AUTHOR]

We present a multiple-person tracking algorithm, based on combining particle filters (PFs) and reciprocal velocity obstacle (RVO), an agent-based crowd model that infers collision-free velocities so as to predict a pedestrian’s motion. In addition to position and velocity, our tracking algorithm can estimate the internal goals (desired destination or desired velocity) of the tracked pedestrian in an online manner, thus removing the need to specify this information beforehand. Furthermore, we leverage the longer term predictions of RVO by deriving a higher order PF, which aggregates multiple predictions from different prior time steps. This yields a tracker that can recover from short-term occlusions and spurious noise in the appearance model. Experimental results show that our tracking algorithm is suitable for predicting pedestrians’ behaviors online without needing scene priors or hand-annotated goal information, and improves tracking in real-world crowded scenes under low frame rates. [ABSTRACT FROM PUBLISHER]

Due to the profitability and selfishness of crowdfunding system users, under fixed budget conditions, there are problems, such as low task completion rate due to insufficient participants and low data quality. However, the existing incentive mechanisms are mainly based on traditional economics, which believes that whether users participate in tasks depends on whether the benefits of the task outweigh the costs. Behavioral economics shows that people judge the value of gains and losses according to a reference point. The weight given to losses is more important than the weight given to the same gains. Therefore, this article considers the impact of reference dependency and loss aversion on user decision-making and proposes a participant selection mechanism based on reference dependency (PSM-RD) and a quality assurance mechanism based on loss aversion (QAM-LA). PSM-RD uses reference points to influence user pricing and selects more participants based on relative value. QAM-LA pays additional rewards based on the data quality of participants and motivates them to improve data quality by reconstructing utility functions. The simulation results show that compared with the ABSee mechanism, data quality has improved by 17%, and the value of completed tasks has increased by at least 40%. [ABSTRACT FROM AUTHOR]

Physical behaviors (e.g., physical activity and sedentary behavior) have been the focus among many researchers in the biomedical and behavioral science fields. The recent shift from hip- to wrist-worn accelerometers in these fields has signaled the need to develop novel approaches to process raw acceleration data of physical activity and sedentary behavior. However, there is currently no consensus regarding the best practices for analyzing wrist-worn accelerometer data to accurately predict individuals' energy expenditure and the times spent in different intensities of free-living physical activity and sedentary behavior. To this end, accurately analyzing and interpreting wrist-worn accelerometer data has become a major challenge facing many clinicians and researchers. In response, this paper attempts to review different methodologies for analyzing wrist-worn accelerometer data and offer cutting edge, yet appropriate analysis plans for wrist-worn accelerometer data in the assessment of physical behavior. In this paper, we first discuss the fundamentals of wrist-worn accelerometer data, followed by various methods of processing these data (e.g., cut points, steps per minute, machine learning), and then we discuss the opportunities, challenges, and directions for future studies in this area of inquiry. This is the most comprehensive review paper to date regarding the analysis and interpretation of free-living physical activity data derived from wrist-worn accelerometers, aiming to help establish a blueprint for processing wrist-derived accelerometer data. [ABSTRACT FROM AUTHOR]

• Steel slag inspired Supersulfate cement hydrated 28-day compressive strength exceeding 50 MPa. • Excessive steel slag causes the hydration of Supersulfate cements to produce expansive Ettringite. • The optimum dosage of steel slag as alkaline exciter is 10%. In order to investigate the feasibility of steel slag as an alkaline exciter for supersulfated cement, the effects of different steel slag dosages on the properties of supersulfated cement were studied. The results show that when steel slag is used as alkaline exciter, the compressive strength and softening coefficient of supersulfate cement increase and then decrease with the increase of steel slag dosage, and the increase of steel slag dosage accelerates the hydration of slag, forming more hydration products of Ettringite and C-S-H gel. Steel slag dosage in 10% of the best results, excessive steel slag will generate expansion of Ettringite, resulting in expansion of the cement matrix structure cracking, is not conducive to the development of strength. [ABSTRACT FROM AUTHOR]

Action segmentation is an emerging task in video understanding, particularly for untrimmed videos containing multiple actions. However, existing video-based methods may struggle due to their sensitivity to visual factors, while skeleton-based methods may not capture sufficient information from human poses to accurately segment actions. To overcome this limitation, we propose a novel approach that leverages the complementary information of video and human poses synergistically for action segmentation. To the best of our knowledge, this is the first attempt to exploit the complementarity of video and poses for this task. Specifically, we introduce a cross-modal salient sampling module that attentively integrates human pose information with temporal visual features for action segmentation across modalities. Our approach achieves state-of-the-art performance on two benchmarks, demonstrating the efficacy of our method in leveraging both visual and pose information for action segmentation. [ABSTRACT FROM AUTHOR]

Examines the precipitation in the Nickel-Titanium-Niobium alloy during annealing in China. Use of XRD, TEM, and energy dispersive X-ray on the precipitation process of Ni-Ti-Nb specimens; Occurrence of diffusional transformation on heat treatment; Level of temperature of precipitation.

In this paper, we introduce a novel yet challenging research problem, interactive crowd video generation, committed to producing diverse and continuous crowd video, and relieving the difficulty of insufficient annotated real-world datasets in crowd analysis. Our goal is to recursively generate realistic future crowd video frames given few context frames, under the user-specified guidance, namely individual positions of the crowd. To this end, we propose a deep network architecture specifically designed for crowd video generation that is composed of two complementary modules, each of which combats the problems of crowd dynamic synthesis and appearance preservation respectively. Particularly, a spatio-temporal transfer module is proposed to infer the crowd position and structure from guidance and temporal information, and a point-aware flow prediction module is presented to preserve appearance consistency by flow-based warping. Then, the outputs of the two modules are integrated by a self-selective fusion unit to produce an identity-preserved and continuous video. Unlike previous works, we generate continuous crowd behaviors beyond identity annotations or matching. Extensive experiments show that our method is effective for crowd video generation. More importantly, we demonstrate the generated video can produce diverse crowd behaviors and be used for augmenting different crowd analysis tasks, i.e., crowd counting, anomaly detection, crowd video prediction. Code is available at https://github.com/Icep2020/CrowdGAN. [ABSTRACT FROM AUTHOR]

The development of innovative technology, such as virtual reality (VR), has provided opportunities for promoting physical activity (PA) in a fun and engaging manner. The purpose of this study was to examine differences in young adults' situational motivation (SM) among immersive VR, non-immersive VR, and traditional stationary cycling sessions. In all, 49 healthy college students (35 females; Mage = 23.6 years, SD = 3.4; M%BF = 24.0%, SD = 7.5) completed three separate 20 min cycling sessions: (1) immersive VR cycling; (2) non-immersive VR cycling; and (3) traditional cycling. Participants' SM was assessed via the situational motivation scale, which included four subconstructs: intrinsic motivation, identified regulation, external regulation, and amotivation. Repeated measures ANOVAs indicated significant differences for situational motivation between cycling sessions (F (2, 96) = 4.74–53.04, p < 0.01, ηp2 = 0.090–0.525). Specifically, participants elicited the highest level of intrinsic motivation in immersive VR cycling compared to the other two sessions. Moreover, participants in both immersive VR and traditional cycling showed greater identified regulation than the non-immersive VR session. Furthermore, participants showed greater external regulation compared to the immersive VR session. In addition, greater amotivation was observed in non-immersive VR compared to the immersive VR session. Findings suggested that immersive VR exercise has the potential to be an attractive exercise alternative, possibly promoting greater PA participation and adherence among young adults. [ABSTRACT FROM AUTHOR]

Synthesizing high dynamic range (HDR) images from multiple low-dynamic range (LDR) exposures in dynamic scenes is challenging. There are two major problems caused by the large motions of foreground objects. One is the severe misalignment among the LDR images. The other is the missing content due to the over-/under-saturated regions caused by the moving objects, which may not be easily compensated for by the multiple LDR exposures. Thus, it requires the HDR generation model to be able to properly fuse the LDR images and restore the missing details without introducing artifacts. To address these two problems, we propose in this paper a novel GAN-based model, HDR-GAN, for synthesizing HDR images from multi-exposed LDR images. To our best knowledge, this work is the first GAN-based approach for fusing multi-exposed LDR images for HDR reconstruction. By incorporating adversarial learning, our method is able to produce faithful information in the regions with missing content. In addition, we also propose a novel generator network, with a reference-based residual merging block for aligning large object motions in the feature domain, and a deep HDR supervision scheme for eliminating artifacts of the reconstructed HDR images. Experimental results demonstrate that our model achieves state-of-the-art reconstruction performance over the prior HDR methods on diverse scenes. [ABSTRACT FROM AUTHOR]

This paper introduces a method for high-resolution lattice image reconstruction and dislocation analysis based on diffraction extinction. The approach primarily involves locating extinction spots in the Fourier transform spectrum (reciprocal space) and constructing corresponding diffraction wave functions. By the coherent combination of diffraction and transmission waves, the lattice image of the extinction planes is reconstructed. This lattice image is then used for dislocation localization, enabling the observation and analysis of crystal planes that exhibit electron diffraction extinction effects and atomic jump arrangements during high-resolution transmission electron microscopy (HRTEM) characterization. Furthermore, due to the method's effectiveness in localizing dislocations, it offers a unique advantage when analyzing high-resolution images with relatively poor quality. The feasibility of this method is theoretically demonstrated in this paper. Additionally, the method was successfully applied to observed edge dislocations, such as 1 / 6 [ 21 1 − ] , 1 / 6 [ 2 − 1 1 − ] , and 1 / 2 [ 0 1 − 1 ] , which are not easily observable in conventional HRTEM characterization processes, in electro-deposited Cu thin films. The Burgers vectors were determined. Moreover, this paper also attempted to observe screw dislocations that are challenging to observe in high-resolution transmission electron microscopy. By shifting a pair of diffraction extinction spots and superimposing the reconstructed images before and after the shift, screw dislocations with a Burgers vector of 1 / 2 [ 01 1 − ] were successfully observed in electro-deposited Cu thin films. [ABSTRACT FROM AUTHOR]

Supervoxel segmentation algorithm has been applied as a preprocessing step for many vision tasks. However, existing supervoxel segmentation algorithms cannot generate hierarchical supervoxel segmentation well preserving the spatiotemporal boundaries in real time, which prevents the downstream applications from accurate and efficient processing. In this paper, we propose a real-time hierarchical supervoxel segmentation algorithm based on the minimum spanning tree (MST), which achieves state-of-the-art accuracy meanwhile at least $11\times $ faster than existing methods. In particular, we present a dynamic graph updating operation into the iterative construction process of the MST, which can geometrically decrease the numbers of vertices and edges. In this way, the proposed method is able to generate arbitrary scales of supervoxels on the fly. We prove the efficiency of our algorithm that can produce hierarchical supervoxels in the time complexity of $O(n)$ , where $n$ denotes the number of voxels in the input video. Quantitative and qualitative evaluations on public benchmarks demonstrate that our proposed algorithm significantly outperforms the state-of-the-art algorithms in terms of supervoxel segmentation accuracy and computational efficiency. Furthermore, we demonstrate the effectiveness of the proposed method on a downstream application of video object segmentation. [ABSTRACT FROM AUTHOR]

Mobile devices usually mount a depth sensor to resolve ill-posed problems, like salient object detection on cluttered background. The main barrier of exploring RGBD data is to handle the information from two different modalities. To cope with this problem, in this paper, we propose a boundary-aware cross-modal fusion network for RGBD salient object detection. In particular, to enhance the fusion of color and depth features, we present a cross-modal feature sampling module to balance the contribution of the RGB and depth features based on the statistics of their channel values. In addition, in our multi-scale dense fusion network architecture, we not only incorporate edge-sensitive losses to preserve the boundary of the detected salient region, but also refine its structure by merging the estimated saliency maps of different scales. We accomplish the multi-scale saliency map merging using two alternative methods which produce refined saliency maps via per-pixel weighted combination and an encoder-decoder network. Extensive experimental evaluations demonstrate that our proposed framework can achieve the state-of-the-art performance on several public RGBD-based datasets. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel method to generate stereoscopic images from light-field images with the intended depth range and simultaneously perform image super-resolution. Subject to the small baseline of neighboring subaperture views and low spatial resolution of light-field images captured using compact commercial light-field cameras, the disparity range of any two subaperture views is usually very small. We propose a method to control the disparity range of the target stereoscopic images with linear or nonlinear disparity scaling and properly resolve the disocclusion problem with the aid of a smooth energy term previously used for texture synthesis. The left and right views of the target stereoscopic image are simultaneously generated by a unified optimization framework, which preserves content coherence between the left and right views by a coherence energy term. The disparity range of the target stereoscopic image can be larger than that of the input light field image. This benefits many light field image-based applications, e.g., displaying light field images on various stereo display devices and generating stereoscopic panoramic images from a light field image montage. An extensive experimental evaluation demonstrates the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Developing a safe and efficient collision-avoidance policy for multiple robots is challenging in the decentralized scenarios where each robot generates its paths with limited observation of other robots' states and intentions. Prior distributed multi-robot collision-avoidance systems often require frequent inter-robot communication or agent-level features to plan a local collision-free action, which is not robust and computationally prohibitive. In addition, the performance of these methods is not comparable with their centralized counterparts in practice. In this article, we present a decentralized sensor-level collision-avoidance policy for multi-robot systems, which shows promising results in practical applications. In particular, our policy directly maps raw sensor measurements to an agent's steering commands in terms of the movement velocity. As a first step toward reducing the performance gap between decentralized and centralized methods, we present a multi-scenario multi-stage training framework to learn an optimal policy. The policy is trained over a large number of robots in rich, complex environments simultaneously using a policy-gradient-based reinforcement-learning algorithm. The learning algorithm is also integrated into a hybrid control framework to further improve the policy's robustness and effectiveness. We validate the learned sensor-level collision-3avoidance policy in a variety of simulated and real-world scenarios with thorough performance evaluations for large-scale multi-robot systems. The generalization of the learned policy is verified in a set of unseen scenarios including the navigation of a group of heterogeneous robots and a large-scale scenario with 100 robots. Although the policy is trained using simulation data only, we have successfully deployed it on physical robots with shapes and dynamics characteristics that are different from the simulated agents, in order to demonstrate the controller's robustness against the simulation-to-real modeling error. Finally, we show that the collision-avoidance policy learned from multi-robot navigation tasks provides an excellent solution for safe and effective autonomous navigation for a single robot working in a dense real human crowd. Our learned policy enables a robot to make effective progress in a crowd without getting stuck. More importantly, the policy has been successfully deployed on different types of physical robot platforms without tedious parameter tuning. Videos are available at https://sites.google.com/view/hybridmrca. [ABSTRACT FROM AUTHOR]

Objective: The purpose of this study was to investigate the associations between mobile phone dependency, bedtime procrastination, FoMO, and sleep quality among college students during the COVID-19 outbreak. Specifically, we examined whether bedtime procrastination and FoMO mediate the relationship between mobile phone dependency and sleep quality. Methods: A total of 881 college students completed an online survey in May 2022 in Shanghai, China. Mobile Phone Involvement Questionnaire, Bedtime Procrastination Scale, Fear of Missing Out Scale and Pittsburgh Sleep Quality Index were used to assess mobile phone dependency, bedtime procrastination, fear of missing out, and sleep quality, respectively. Multiple linear regression and mediation analysis were conducted. Results: The correlation analyses indicated mobile phone dependency was positively associated with fear of missing out, bedtime procrastination, and poor sleep quality among college students. The structural equation modeling analyses revealed that mobile phone dependency had significant indirect effects on sleep quality through bedtime procrastination (indirect effect: 0.030, 95%CI: 0.022–0.041) and fear of missing out (indirect effect: 0.013, 95%CI: 0.003–0.023). Conclusion: The findings indicated that bedtime procrastination and fear of missing out are mediators mediating the relationship between mobile phone dependency with sleep quality. Bedtime procrastination and fear of missing out should be considered as potential intervention targets for reducing mobile phone dependency and improving sleep quality in college students. [ABSTRACT FROM AUTHOR]

Aim: This study examined the relationships between energy balance-related behaviours (EBRBs) outside school hours and obesity in Chinese primary school students. We also explored the influence of gender on those relationships.Methods: The study sample was a cross-sectional cohort of 5032 Chinese children who were enrolled in grades 1-6 in primary schools in five Chinese cities and whose mean ages ranged from seven years and three months to 11.9 years. The children's parents completed a survey on their child's height, weight and EBRBs outside school hours.Results: The response rate was 97%, and the reported rates of overweight and obesity were 13.6% and 13.8%, respectively. The obesity rates were higher in boys and lower grade children. Most EBRBs varied between boys and girls and with increased grade levels. The amount of time spent on academic-related activities, screen viewing, outdoor activities and sleep was mostly associated with obesity on weekdays and varied by gender.Conclusion: Rate of obesity was alarmingly high in the primary school Chinese children in this cohort, especially in younger children. Excessive time spent on academic-related activities outside school hours, inadequate sleep, physical inactivity and higher levels of screen viewing were major contributors to obesity in these Chinese children. [ABSTRACT FROM AUTHOR]

Existing computational models for salient object detection primarily rely on hand-crafted features, which are only able to capture low-level contrast information. In this paper, we learn the hierarchical contrast features by formulating salient object detection as a binary labeling problem using deep learning techniques. A novel superpixelwise convolutional neural network approach, called SuperCNN, is proposed to learn the internal representations of saliency in an efficient manner. In contrast to the classical convolutional networks, SuperCNN has four main properties. First, the proposed method is able to learn the hierarchical contrast features, as it is fed by two meaningful superpixel sequences, which is much more effective for detecting salient regions than feeding raw image pixels. Second, as SuperCNN recovers the contextual information among superpixels, it enables large context to be involved in the analysis efficiently. Third, benefiting from the superpixelwise mechanism, the required number of predictions for a densely labeled map is hugely reduced. Fourth, saliency can be detected independent of region size by utilizing a multiscale network structure. Experiments show that SuperCNN can robustly detect salient objects and outperforms the state-of-the-art methods on three benchmark datasets. [ABSTRACT FROM AUTHOR]

We introduce a novel, online method to predict pedestrian trajectories using agent-based velocity-space reasoning for improved human–robot interaction and collision-free navigation. Our formulation uses velocity obstacles to model the trajectory of each moving pedestrian in a robot’s environment and improves the motion model by adaptively learning relevant parameters based on sensor data. The resulting motion model for each agent is computed using statistical inferencing techniques, including a combination of ensemble Kalman filters and a maximum-likelihood estimation algorithm. This allows a robot to learn individual motion parameters for every agent in the scene at interactive rates. We highlight the performance of our motion prediction method in real-world crowded scenarios, compare its performance with prior techniques, and demonstrate the improved accuracy of the predicted trajectories. We also adapt our approach for collision-free robot navigation among pedestrians based on noisy data and highlight the results in our simulator. [ABSTRACT FROM PUBLISHER]

Objective: Given the low levels of physical activity (PA) among U.S. college students, the use of exergaming as a supplement to traditional exercise may promote higher levels of motivation and PA. Therefore, this study's purpose was to examine the effect of two different exergames on college students' situational interest (SI), self-efficacy (SE), and equilibrium change (EQC) compared to traditional treadmill walking. Methods: Sixty college students (30 female; Mage = 23.6 ± 4.1 years; MBMI = 23.9 ± 4.0 kg/m2) participated in three separate 20 min exercise sessions: (1) Xbox 360 Kinect Just Dance; (2) Xbox 360 Kinect Reflex Ridge; and (3) traditional treadmill walking at 4.0 mph. Participants' SI, SE, and EQC were measured after each session using a series of validated surveys. Results: A mixed model analysis of covariance (ANCOVA) with repeated measures evaluated mean differences between exercise sessions for all outcomes. Significant main effects were observed between the three exercise sessions (all p < 0.01). Specifically, Just Dance and Reflex Ridge sessions yielded significantly higher SI scores than treadmill exercise, F (10, 49) = 54.61, p < 0.01, η2 = 0.92. In addition, participants experienced significantly lower EQC in Reflex Ridge than in treadmill exercise, F (2, 58) = 4.26, p = 0.02, η2 = 0.13. No differences were identified for SE. Conclusion: The integration of exergaming into traditional exercise routines may help to promote higher levels of SI but not SE amongst college students. RR exergaming also demonstrated low EQC as compared to traditional exercise. Experimental study designs are warranted to provide additional evidence on the efficacy of exergaming. [ABSTRACT FROM AUTHOR]

Semantic segmentation is one of the directions in image research. It aims to obtain the contours of objects of interest, facilitating subsequent engineering tasks such as measurement and feature selection. However, existing segmentation methods still lack precision in class edge, particularly in multi-class mixed region. To this end, we present the Feature Enhancement Network (FE-Net), a novel approach that leverages edge label and pixel-wise weights to enhance segmentation performance in complex backgrounds. Firstly, we propose a Smart Edge Head (SE-Head) to process shallow-level information from the backbone network. It is combined with the FCN-Head and SepASPP-Head, located at deeper layers, to form a transitional structure where the loss weights gradually transition from edge labels to semantic labels and a mixed loss is also designed to support this structure. Additionally, we propose a pixel-wise weight evaluation method, a pixel-wise weight block, and a feature enhancement loss to improve training effectiveness in multi-class regions. FE-Net achieves significant performance improvements over baselines on publicly datasets Pascal VOC2012, SBD, and ATR, with best mIoU enhancements of 15.19%, 1.42% and 3.51%, respectively. Furthermore, experiments conducted on Pole&Hole match dataset from our laboratory environment demonstrate the superior effectiveness of FE-Net in segmenting defined key pixels. [ABSTRACT FROM AUTHOR]

Domain Generalization (DG) aims to generalize a model trained on multiple source domains to an unseen target domain. The source domains always require precise annotations, which can be cumbersome or even infeasible to obtain in practice due to the vast amount of data involved. Web data, namely web-crawled images, offers an opportunity to access large amounts of unlabeled images with rich style information, which can be leveraged to improve DG. From this perspective, we introduce a novel paradigm of DG, termed as Semi-Supervised Domain Generalization (SSDG) , to explore how the labeled and unlabeled source domains can interact, and establish two settings, including the close-set and open-set SSDG. The close-set SSDG is based on existing public DG datasets, while the open-set SSDG, built on the newly-collected web-crawled datasets, presents a novel yet realistic challenge that pushes the limits of current technologies. A natural approach of SSDG is to transfer knowledge from labeled data to unlabeled data via pseudo labeling, and train the model on both labeled and pseudo-labeled data for generalization. Since there are conflicting goals between domain-oriented pseudo labeling and out-of-domain generalization, we develop a pseudo labeling phase and a generalization phase independently for SSDG. Unfortunately, due to the large domain gap, the pseudo labels provided in the pseudo labeling phase inevitably contain noise, which has negative affect on the subsequent generalization phase. Therefore, to improve the quality of pseudo labels and further enhance generalizability, we propose a cyclic learning framework to encourage a positive feedback between these two phases, utilizing an evolving intermediate domain that bridges the labeled and unlabeled domains in a curriculum learning manner. Extensive experiments are conducted to validate the effectiveness of our method. It is worth highlighting that web-crawled images can promote domain generalization as demonstrated by the experimental results. • Developing the close-set and open-set semi-supervised domain generalization (SSDG). • Constructing two web-crawled datasets are for the open-set SSDG. • Establishing strong baselines for SSDG using existing deep learning methods. • Proposing a framework with evolving intermediate domain for SSDG. • The framework outperforms the strong baselines in both close-set and open-set SSDG. [ABSTRACT FROM AUTHOR]

Background: Motor skill competence (MSC) and perceived competence (PC) are primary correlates that are linked with physical activity (PA) participation, yet there is limited evidence of the mutual longitudinal or temporal associations between these variables in preschoolers. Therefore, this study's purpose was to examine the bidirectional relationships between MSC and PA, MSC and PC, and PC and PA in preschoolers over time. Methods: The final sample were 61 preschoolers (Mage = 4.45 years, ranging from 4 to 5) from two underserved schools. MSC was assessed using the Test of Gross Motor Development, Second Edition (TGMD-2). PC was assessed using the Pictorial Scale of Perceived Competence and Social Acceptance for Young Children. PA was assessed using ActiGraph GT9X Link accelerometers during three consecutive school days. All assessments of MSC, PC, and PA were measured in identical conditions at schools at the baseline (T1) and the end of the eighth week (T2). We employed a cross-lagged model approach to understand the bidirectional relationships between MSC, PC, and PA. Results: The results showed that T1 MSC significantly predicted T2 MSC (p < 0.01) and T1 MSC significantly predicted T2 PA only in girls (p = 0.03). Additionally, a cross-lagged effect of T1 MSC and T2 PC was only observed in boys (p = 0.03). Lastly, a significant association for T1 moderate-to-vigorous physical activity (MVPA) and T2 PC was only observed in girls (p = 0.04). Conclusions: Bidirectional relationships between the variables were not observed in preschoolers. However, significant gender differences were observed in each cross-lagged model. [ABSTRACT FROM AUTHOR]

Purpose. The bidirectional associations among children's motor skill competence (MSC), perceived competence (PC), physical activity (PA), and cardiorespiratory fitness (CRF) over time remain unanswered. This study is aimed at discerning the bidirectional relationships among elementary school children's MSC, PC, PA and, CRF over the course of one school year. Methods. A total of 261 second and third grade children (127 boys, 134 girls; mea n age = 8.27 years; BMI = 18.22 ± 3.71) were recruited from two Texas elementary schools. Approximately 73.56% of participants were White American. Children's baseline data were assessed in September/October in 2012 (Time1), and identical assessments were conducted in April/May in 2013 (Time2). MSC was assessed using product-oriented skill tests (e.g., throw, kick, and jump). PC was assessed via the Pictorial Scale of Perceived Competence for Children. Minutes spent in moderate-to-vigorous PA (MVPA) was assessed using ActiGraph GT3X+ accelerometers for five days, and CRF was assessed by the PACER test. Six age- and body mass index-adjusted cross-lagged panel models were used to test the relationships between the variables. Results. We observed that T1 MSC significantly predicted T2 MSC (β = 0.59 ; p < 0.01), T2 CRF (β = 0.28 ; p < 0.01), and T2 MVPA (β = 0.18 ; p < 0.01). Children's CRF was a positive predictor for T2 CRF (β = 0.56 ; p < 0.01) and T2 MSC (β = 0.13 ; p < 0.05) Additionally, T1 MVPA significantly predicted T2 MVPA (β = 0.30 ; p < 0.01) and T2 PC (β = − 0.14 ; p < 0.05). Conclusion. Findings suggested a fully bidirectional relationship between elementary children's MSC and CRF. Other bidirectional relationships among the variables were only partially supported. Educators and health professionals need to emphasize the importance of developing both MSC and CRF to maintain physical health over time. [ABSTRACT FROM AUTHOR]

Objective Purpose. The following review synthesized the currently available literature evaluating the effectiveness of smartphone-based physical activity applications on various health outcomes including physical and physiological outcomes, weight-related outcomes, and psychosocial outcomes. Design. A systematic review. Data Sources. 114 studies were gathered using the following search descriptors: ("mobile phone" OR "smartphone" OR "cell phone" OR "mobile device" OR "mobile apps" OR "mHealth") AND ("exercise" OR "physical activity" OR "physical fitness" OR "motor activity") AND ("physiological outcomes" OR "weight outcomes" OR "psychological outcomes" OR "health" OR "health behavior"). Seven databases were used including databases such as Academic Search Premier and PubMed. PRISMA guidelines were followed in this review. Eligibility Criteria for Selecting Studies. The 20 articles included in this review met the following inclusion criteria: (1) randomized and controlled trials, (2) involving an outcome variable measured by accelerometer, and (3) intervention enforced by a smartphone application. Results. Overall, 56% of the studies reviewed in this paper resulted in successful interventions. Of the 19 articles that examined the first individual health outcome of physical and physiological outcomes, 11 interventions resulted in a positive effect on one of the following parameters: MVPA/step count, sedentary behavior, cardiorespiratory fitness, and blood pressure. Six interventions examined the effects on the second individual health outcome, weight-related outcomes. Five of these interventions observed significant positive effects from mobile application interventions on weight and waist circumference. Six articles evaluated the effectiveness of smartphone-based physical activity interventions on the third and final individual health outcome, psychological outcomes, with four resulting in significant positive outcomes in self-efficacy, life enjoyment/satisfaction, and intrinsic PA motivation. Conclusion. The findings in this review suggest that mobile application physical activity interventions, compared to unguided exercise activities, can effectively improve certain health outcomes for individuals such as physical/physiological and weight-related outcomes. It was found that research in the area of effectiveness of mobile application interventions on specific psychosocial health outcomes such as self-efficacy, life enjoyment, and intrinsic PA motivation is limited. Thus, the effect of mobile health applications remains unclear for psychosocial outcomes. Due to this limitation, more research is warranted to confirm the findings of this review. [ABSTRACT FROM AUTHOR]

Crowd counting is challenging due to unconstrained imaging factors, e.g., background clutters, non-uniform distribution of people, large scale and perspective variations. Dealing with these problems using deep neural networks requires rich prior knowledge and multi-scale contextual representations. In this paper, we propose a Cross-stage Refinement Network (CRNet) that can refine predicted density maps progressively based on hierarchical multi-level density priors. In particular, CRNet is composed of several fully convolutional networks. They are stacked together recursively with the previous output as the next input, and each of them serves to utilize previous density output to gradually correct prediction errors of crowd areas and refine the predicted density maps at different stages. Cross-stage multi-level density priors are further exploited in our recurrent framework by the cross-stage skip layers based on ConvLSTM. To cope with different challenges of unconstrained crowd scenes, we explore different crowd-specific data augmentation methods to mimic real-world scenarios and enrich crowd feature representations from different aspects. Extensive experiments show the proposed method achieves superior performances against state-of-the-art methods on four widely-used challenging benchmarks in terms of counting accuracy and density map quality. Code and models are available at this https://github.com/lytgftyf/Crowd-Counting-via-Cross-stage-Refinement-Networks. [ABSTRACT FROM AUTHOR]

With the advances in commercial light field cameras, light field image processing has attracted considerable attention from researchers. In this paper, we propose a novel method for generating stereoscopic images from a light field image pair with flexible control over the convergence of the virtual stereo cameras. We have developed a light field image-capturing prototype that consists of two horizontally arranged light field cameras (i.e., with their optical axes being parallel to each other). When using our proposed device for image/video capture, stereo photographers can concentrate on how to capture the desired visual experience without being frequently disturbed by having to manipulate the stereo camera parameters, i.e., the convergence angle of a stereo camera. During postprocessing, our method estimates accurate disparity maps for the light field image pair and then generates the target stereoscopic images that satisfy the desired stereo camera convergence requirements by adopting a novel view synthesis method for light field images. We have conducted extensive experiments to demonstrate the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]

Sulfated derivatives of galactomannan from locust bean gum (LBG) with the degree of substitution (DS) of 0.34–1.07 were synthesized using chlorosulfonic acid/pyridine (CSA/Py) method. Box–Behnken design (BBD) of response surface methodology (RSM) was employed to optimize the reaction conditions. Results of FT-IR and X-ray photoelectron spectroscopy (XPS) indicated that SO 3 H groups were widely present in sulfated LBG (SLBG). 13 C NMR result revealed that sulfation had occurred and C-6 substitution was predominant in SLBG. All sulfated samples showed a decrease in M w and more broad molar mass distribution in size exclusion chromatography combined with laser light scattering (SEC-LLS) analysis. Results of M W – 〈 S 2 〉 z 1 / 2 showed a decrease in fractal dimension ( d f ) value. Laser light scattering results also showed a conformation transition from a compact chain conformation of branched clusters to a random coil conformation of SLBG. Compared to LBG and SLBG with low DS and molecular weight, SLBG 2 exhibited an internal structure of random coil with a DS of 1.07. DS and molecular weight had great influence on its conformation in aqueous solution. Our results confirmed that the degradation of polysaccharide and SO 3 H groups improved significantly the stiffness of the chains due to the electrostatic effect. [ABSTRACT FROM AUTHOR]

With NH3·H2O, NH3·H2O-NH4HCO3 buffer solution and NaOH solution as coprecipitation agents, NiO–ZrO2, anode powder of solid oxide fuel cell, was synthesized by coprecipitation methods. Composition accuracy was analyzed by comparing the original composition with the mass of the eventually obtained powder. It was shown that cubic NiO and cubic YSZ with a cascade powder distribution were obtained after the powder was calcined for 1h at different temperatures. Composition analysis of the powder synthesized with NH3·H2O as coprecipitation agent showed that NiO–YSZ powder greatly deviated from the original composition due to the loss of Ni2+ in the form of [Ni(NH3)4]2+. When NH3·H2O–NH4HCO3 buffer solution was used, productive output of nickel was increased. The loss of nickel can be totally avoided and better control of the powder composition could be realized when NaOH was used as coprecipitation agent. [Copyright &y& Elsevier]

In recent years, data imbalance in the conventional classification problem has raised great interest in the industry. However, concerning the rule-based systems, this problem has been rarely investigated. We propose a Belief Rule-Based (BRB) reasoning model based on the evidential reasoning algorithm to fill in the gap by solving the problem caused by imbalanced data with regards to the rule-based systems. It utilizes the data-driven characteristics of Extended Belief Rule-Based (EBRB) and incorporates the data class rebalancing technique with the ensemble learning method of EBRB. In order to increase the number of rules that can promote the correct classification of minority classes in EBRB, we apply an adaptive data resampling strategy to expand the proportion of minority classes. On this basis, the data is divided into several EBRB base learners with different classification characteristics. During the iterative process, the rule weight of the base learner is dynamically adjusted according to the correct and incorrect classification, such that the classifier can pay more attention to the minority classes and reduce the bias of classification. Finally, the optimized EBRB base learner is selected to build an ensemble classifier with excellent classification performance. Experiments on 27 binary class and 12 multi-class imbalanced datasets show that our approach significantly improves F-value and MACC compared with other imbalanced classification algorithms. By building a cascaded EBRB model, the activation weight is taken as the basis of model evolution, the application limitations of the EBRB model in the ensemble learning are solved innovatively, and the classification performance of the EBRB model for imbalanced data is improved significantly. [ABSTRACT FROM AUTHOR]

Purpose: This feasibility study investigated whether a year-long combined fitness wristband-based and personalized exercise prescription intervention improves Chinese breast cancer survivors' (BCSs) health outcomes. Methods: Ninety-five BCSs (X age = 44.81 ± 7.94; X BMI = 22.18 ± 3.48) were recruited from Southern region of China and were delivered the exercise intervention across 12 months, using a single group pretest–posttest design. Participants' lipid profile (e.g., total cholesterol, high-density lipoprotein, low-density lipoprotein, and triglycerides), blood glucose, breast cancer biomarkers (e.g., carcinoembryonic antigen and cancer antigen 15-3), and functional fitness (e.g., strength in arms and legs, endurance, balance, agility, and flexibility) were assessed at baseline and 12-month post-intervention. Results: Thirty-three BCSs successfully completed the intervention. A significant change in blood glucose (mean difference (MD): −0.22, 95% confidence interval (CI): −0.41–−0.03, t = −2.25, p = 0.028) was observed, with participants demonstrating lower levels of blood glucose at the 12-month post-intervention versus the baseline assessment. Notable changes in functional fitness were also discerned, including agility and balance (MD: −0.47, 95% CI: −0.68–−0.26, t = −4.336, p < 0.001), aerobic endurance (MD: 89.25, 95% CI: 73.82–104.68, t = 11.336, p < 0.001), lower-body flexibility (left) (MD: 4.58, 95% CI: −4.4–13.56, t = 4.653, p < 0.001), and lower-body flexibility (right) (MD: 4.84, 95% CI: −4.65–14.33, t = 4.092, p < 0.001). Conclusion: The observations suggested that our behavioral change program might promote certain health outcomes in Chinese BCSs, yet we are unable to recommend such a program given existing limitations. Future randomized control trials with diverse samples are warranted to confirm our findings. [ABSTRACT FROM AUTHOR]

• Deep compression of these deterministic models has been proposed in last few years to reduce the number of connections and nodes, while remaining the classification accuracy of these models. This paper is the first attempt to combine deep probabilistic graphical networks (PGNs) and deep compression techniques together to derive sparse versions of the deep probabilistic models. • The developed pruning approach is a layer-by-layer and pre-pruning one. That is, the final PGNs grow in a layer-by-layer and compressed manner. It is very efficient in redundancy reduction. The whole pruning only takes a few seconds to conduct, while other complex methods take much more time to select sparse architectures or conduct model compression, such as regularization and low-rank factorization approaches. These model compression techniques are more time-consuming compared with pruning due to the complexity of regularization and factorization. • The correctness and efficiency of the proposed compression approach are evaluated by a number of PGNs with different datasets. It can be used to compress trained PGNs to achieve a lightweight network which can be embedded in on-chip memory of small mobile devices. It is also flexible to implement and can be generalized to other deep PGNs. Probabilistic Graphical Models (PGMs) are important and active research areas in machine learning and artificial intelligence. The well-known representatives of PGMs include Restricted Boltzmann Machines (RBMs), Deep Belief Networks (DBNs), Deep Boltzmann Machines (DBMs), and their variants. These PGMs open a new dimension of machine learning and directly lead to the revival of deep learning since 2006. Compared with deep deterministic models, such as deep convolutional neural networks (CNNs), PGMs are more flexible, robust and powerful for both unsupervised and supervised learning problems. As the generative models on the one hand, PGMs have the good capability of generating samples after extracting informative features of input data. On the other hand, they also can provide a good initialization of hierarchical structures for supervised learning. The PGMs with deep structures are called deep Probabilistic Graphical Networks (PGNs) due to their hierarchical structures and close relationships with deep neural networks. There are a large number of CNN-based deep deterministic networks proposed for computer vision tasks. However, these deep deterministic models are shown to possess extremely large number of model parameters, and have serious redundancy problems. Therefore, deep compression of these deterministic models have been proposed in the last few years to reduce the number of connections and nodes, while preserving the classification accuracy. This paper is the first attempt to combine deep PGNs and deep compression techniques together to derive sparse versions of the deep probabilistic models. We firstly examine that whether deep PGNs have serious problem of parameter redundancy, and compress them if necessary. From the experimental results on MNIST, Fashion-MNIST and CIFAR-10 dataset, deep PGNs can be compressed by at least 50% of their parameters through a deep pruning and retraining approach, while keeping their capabilities in both generative and discriminative tasks. [ABSTRACT FROM AUTHOR]