Accurate and efficient modeling of large-scale urban scenes is critical for applications such as AR navigation, UAV-based inspection, and smart city digital twins. While aerial imagery offers broad coverage and complements limitations of ground-based data, reconstructing city-scale environments from such views remains challenging due to occlusions, incomplete geometry, and high memory demands. Recent advances like 3D Gaussian Splatting (3DGS) improve scalability and visual quality but remain limited by dense primitive usage, long training times, and poor suitability for edge devices. We propose CityGo, a hybrid framework that combines textured proxy geometry with residual and surrounding 3D Gaussians for lightweight, photorealistic rendering of urban scenes from aerial perspectives. Our approach first extracts compact building proxy meshes from MVS point clouds, then uses zero-order SH Gaussians to generate occlusion-free textures via image-based rendering and back-projection. To capture high-frequency details, we introduce residual Gaussians placed based on proxy-photo discrepancies and guided by depth priors. Broader urban context is represented by surrounding Gaussians, with importance-aware downsampling applied to non-critical regions to reduce redundancy. A tailored optimization strategy jointly refines proxy textures and Gaussian parameters, enabling real-time rendering of complex urban scenes on mobile GPUs with significantly reduced training and memory requirements. Extensive experiments on real-world aerial datasets demonstrate that our hybrid representation achieves fastest training speed, while delivering comparable visual fidelity to pure 3D Gaussian Splatting approaches. Furthermore, CityGo enables real-time rendering of large-scale urban scenes on mobile consumer GPUs, with substantially reduced memory usage and energy consumption.

Large garages are ubiquitous yet intricate scenes that present unique challenges due to their monotonous colors, repetitive patterns, reflective surfaces, and transparent vehicle glass. Conventional Structure from Motion (SfM) methods for camera pose estimation and 3D reconstruction often fail in these environments due to poor correspondence construction. To address these challenges, we introduce LetsGo, a LiDAR-assisted Gaussian splatting framework for large-scale garage modeling and rendering. We develop a handheld scanner, Polar, equipped with IMU, LiDAR, and a fisheye camera, to facilitate accurate data acquisition. Using this Polar device, we present the GarageWorld dataset, consisting of eight expansive garage scenes with diverse geometric structures, which will be made publicly available for further research. Our approach demonstrates that LiDAR point clouds collected by the Polar device significantly enhance a suite of 3D Gaussian splatting algorithms for garage scene modeling and rendering. We introduce a novel depth regularizer that effectively eliminates floating artifacts in rendered images. Additionally, we propose a multi-resolution 3D Gaussian representation designed for Level-of-Detail (LOD) rendering. This includes adapted scaling factors for individual levels and a random-resolution-level training scheme to optimize the Gaussians across different resolutions. This representation enables efficient rendering of large-scale garage scenes on lightweight devices via a web-based renderer. Experimental results on our GarageWorld dataset, as well as on ScanNet++ and KITTI-360, demonstrate the superiority of our method in terms of rendering quality and resource efficiency.

The multivariate fusion transformation is ubiquitous in multivariate time series prediction (MTSP) problems. The previous multivariate fusion transformation fuses the feature of different variates at a time step, then projects them to a new feature space for effective feature representation. However, temporal dependency is the most fundamental property of time series. The previous manner fails to capture the temporal dependency of the feature, which is destroyed in the transformed feature matrix. Multivariate feature extraction based on the feature matrix with missing temporal dependency leads to the loss of predictive performance of MTSP. To address this problem, we propose the Temporal Dependency Priority for Multivariate Time Series Prediction (TemDep) method. Specifically, TemDep extracts feature temporal dependency of multivariate time series first and then considers multivariate feature fusion. Moreover, the low-dimensional and high-dimensional feature fusion manners are designed with the temporal dependency priority to fit different dimensional multivariate time series. The extensive experimental results of different datasets show that our proposed method can outperform all state-of-the-art baseline methods. It proves the significance of temporal dependency priority for MTSP.

In the field of financial prediction, most studies focus on individual stocks or stock indices. Stock sectors are collections of stocks with similar characteristics and the indices of sectors have more stable trends and predictability compared to individual stocks. Additionally, stock sectors are subsets of stock indices, which implies that investment portfolios based on stock sectors have a greater potential to achieve excess returns. In this paper, we propose a new method, Time-aware Graph Structure Learning Network (TGSLN), to address the problem of stock sector ranking recommendation. In this model, we use an indicator called Relative Price Strength (RPS) to describe the ranking change trend of the sectors. To construct the inherent connection between sectors, we construct a multi-variable time series that consists of multi-scale RPS sequences and effective indicators filtered through the factor selector. We also build a stock sector relation graph based on authoritative stock sector classifications. Specially, we design a time-aware graph structure learner, which can mine the sector relations from time series, and enhance the initial graph through graph fusion. Our model outperforms state-of-the-art baselines in both A-share and NASDAQ markets.

We have recently seen tremendous progress in the neural advances for photo-real human modeling and rendering. However, it's still challenging to integrate them into an existing mesh-based pipeline for downstream applications. In this paper, we present a comprehensive neural approach for high-quality reconstruction, compression, and rendering of human performances from dense multi-view videos. Our core intuition is to bridge the traditional animated mesh workflow with a new class of highly efficient neural techniques. We first introduce a neural surface reconstructor for high-quality surface generation in minutes. It marries the implicit volumetric rendering of the truncated signed distance field (TSDF) with multi-resolution hash encoding. We further propose a hybrid neural tracker to generate animated meshes, which combines explicit non-rigid tracking with implicit dynamic deformation in a self-supervised framework. The former provides the coarse warping back into the canonical space, while the latter implicit one further predicts the displacements using the 4D hash encoding as in our reconstructor. Then, we discuss the rendering schemes using the obtained animated meshes, ranging from dynamic texturing to lumigraph rendering under various bandwidth settings. To strike an intricate balance between quality and bandwidth, we propose a hierarchical solution by first rendering 6 virtual views covering the performer and then conducting occlusion-aware neural texture blending. We demonstrate the efficacy of our approach in a variety of mesh-based applications and photo-realistic free-view experiences on various platforms, i.e., inserting virtual human performances into real environments through mobile AR or immersively watching talent shows with VR headsets.

Development of authorization mechanisms for secure information access by a large community of users in an open environment is an important problem in the ever-growing Internet world. In this paper we propose a computational dynamic trust model for user authorization, rooted in findings from social science. Unlike most existing computational trust models, this model distinguishes trusting belief in integrity from that in competence in different contexts and accounts for subjectivity in the evaluation of a particular trustee by different trusters. Simulation studies were conducted to compare the performance of the proposed integrity belief model with other trust models from the literature for different user behavior patterns. Experiments show that the proposed model achieves higher performance than other models especially in predicting the behavior of unstable users.

The popularity of online auctions and the associated frauds have led to many auction sites preferring English auction over other auction mechanisms. The ease of adopting multiple fake identities over the Internet nourishes shill bidding by fraudulent sellers in English auction. In this paper, we derive an equilibrium bidding strategy to counteract shill bidding in an online English auction. An algorithm based on this strategy is developed. We conduct experiments to evaluate the strategy in a simulated eBay like auction environment. Five popular bidding strategies are compared with the proposed one. In the simulation, bidders compete to buy a product in the presence of a shill. Each bidder is randomly assigned a bidding strategy. She draws her valuation from a uniform distribution. The experiments show hat the average expected utility of agents with proposed strategy is the highest when the auction continues for a longer duration.

We investigate the performance issues of destination-sequenced distance vector (DSDV) and ad-hoc on-demand distance vector (AODV) routing protocols for mobile ad hoc networks. Four performance metrics are measured by varying the maximum speed of mobile hosts, the number of connections, and the network size. The correlation between network topology change and mobility is investigated by using linear regression analysis. The simulation results indicate that AODV outperforms DSDV in less stressful situations, while DSDV is more scalable with respect to the network size. It is observed that network congestion is the dominant reason for packet drop for both protocols. We propose a new routing protocol, congestion-aware distance vector (CADV), to address the congestion issues. CADV outperforms AODV in delivery ratio by about 5%, while introduces less protocol load. The result demonstrates that integrating congestion avoidance mechanisms with proactive routing protocols is a promising way to improve performance.