Generating sketches that accurately reflect the content of reference images presents numerous challenges. Current methods either require paired training data or fail to accommodate a wider range and diversity of sketch styles. While pre-trained diffusion models have shown strong text-based control capabilities for reference-based content sketch generation, state-of-the-art methods still struggle with reference-based sketch generation for given content. The main difficulties lie in (1) balancing content preservation with style enhancement, and (2) representing content image textures at varying levels of abstraction to approximate the reference sketch style. In this paper, we propose a method (Ref2Sketch-SA) that transforms a given content image into a sketch based on a reference sketch. The core strategies include (1) using DDIM Inversion to enhance structural consistency in the sketch generation of content images; (2) injecting noise into the input image during the denoising process to produce a sketch that retains content attributes while aligning with, yet differing in texture from, the reference. Our model demonstrates superior performance across multiple evaluation metrics, including user style preference.

Generating sketches guided by reference styles requires precise transfer of stroke attributes, such as line thickness, deformation, and texture sparsity, while preserving semantic structure and content fidelity. To this end, we propose Stroke2Sketch, a novel training-free framework that introduces cross-image stroke attention, a mechanism embedded within self-attention layers to establish fine-grained semantic correspondences and enable accurate stroke attribute transfer. This allows our method to adaptively integrate reference stroke characteristics into content images while maintaining structural integrity. Additionally, we develop adaptive contrast enhancement and semantic-focused attention to reinforce content preservation and foreground emphasis. Stroke2Sketch effectively synthesizes stylistically faithful sketches that closely resemble handcrafted results, outperforming existing methods in expressive stroke control and semantic coherence. Codes are available at https://github.com/rane7/Stroke2Sketch.

Current sketch extraction methods either require extensive training or fail to capture a wide range of artistic styles, limiting their practical applicability and versatility. We introduce Mixture-of-Self-Attention (MixSA), a training-free sketch extraction method that leverages strong diffusion priors for enhanced sketch perception. At its core, MixSA employs a mixture-of-self-attention technique, which manipulates self-attention layers by substituting the keys and values with those from reference sketches. This allows for the seamless integration of brushstroke elements into initial outline images, offering precise control over texture density and enabling interpolation between styles to create novel, unseen styles. By aligning brushstroke styles with the texture and contours of colored images, particularly in late decoder layers handling local textures, MixSA addresses the common issue of color averaging by adjusting initial outlines. Evaluated with various perceptual metrics, MixSA demonstrates superior performance in sketch quality, flexibility, and applicability. This approach not only overcomes the limitations of existing methods but also empowers users to generate diverse, high-fidelity sketches that more accurately reflect a wide range of artistic expressions.

With the rapid development of wireless sensing technology and the popularity of the internet of things, applications based on wireless sensor networks have been applied universally in many scenarios. Sweep coverage is an emerging technique to improve the quality of service by promoting the energy efficiency of the sensors. To solve the distance-sensitive-route scheduling problem, which considering the route scheduling taking advantage of the sensing radius to reduces the cycle path of the mobile sensors and improves the feedback time of the network, this article proposes a three-stage geometry assisted energy-efficient sweep coverage algorithm to determine the route of mobile sensors with minimal energy consumption. With analysis of the distribution of the static monitoring targets, initial sensing points are determined. To minimize the sweep path in a single cycle, we use an ant colony optimization algorithm to schedule an energy-efficient routing. In addition, the sensing point of each target is updated by a local optimization mechanism according to the route information. To demonstrate the effectiveness of the proposed algorithm, we compare our proposed algorithm to a wealth of wireless sensor network scenarios. The simulation results show that our algorithm can significantly reduce the length of the cycle route, so as to enhance the energy efficiency of the wireless sensor networks.

We demonstrate a heuristic approach for optimizing the posterior density of the data association tracking algorithm via the random finite set (RFS) theory. Specifically, we propose an adjusted version of the joint probabilistic data association (JPDA) filter, known as the nearest-neighbor set JPDA (NNSJPDA). The target labels in all possible data association events are switched using a novel nearest-neighbor method based on the Kullback-Leibler divergence, with the goal of improving the accuracy of the marginalization. Next, the distribution of the target-label vector is considered. The transition matrix of the target-label vector can be obtained after the switching of the posterior density. This transition matrix varies with time, causing the propagation of the distribution of the target-label vector to follow a non-homogeneous Markov chain. We show that the chain is inherently doubly stochastic and deduce corresponding theorems. Through examples and simulations, the effectiveness of NNSJPDA is verified. The results can be easily generalized to other data association approaches under the same RFS framework.

Characterized by the ability to handle varying number of objects, tracking by detection framework becomes increasingly popular in multiobject tracking (MOT) problem. However, the tracking performance heavily depends on the object detector. Considering that data association optimization and association affinity model are two key parts in MOT, an online multipedestrian tracking method is proposed to formulate a more effective association affinity model. It includes a two-step data association taking advantage of rank-based dynamic motion affinity model. The rank-based dynamic motion affinity model is used to estimate the object state and refine the trajectory for each of target to achieve the noiseless trajectory. Both strategies are beneficial to eliminate ambiguous detection responses during association. To fairly verify the proposed method, three public datasets are adopted. Both qualitative and quantitative experiment results demonstrate the superiorities of the proposed tracking algorithm in comparison with its counterparts.

Single image super resolution has achieved a significant breakthrough with the development of deep learning technology. Among these approaches based on deep learning, the mainstream method is to build a cascading network and attempt to add more learning layers. However, as the depth of the model increases, features far away from the reconstruction layer are less considered in the reconstruction process. In this paper, we propose a novel model based on a refined densely connected network for super-resolution reconstruction tasks. By utilizing densely connected paths in the model, we can significantly shorten the distance between the feature maps from different levels and the reconstruction layer. Besides, an inception-like structure is employed to replace the ordinary convolutional layer to take full advantage of the contextual information. Moreover, quantities of 1 ×1 filters are used to ensure an acceptable model size. Extensive experiments are conducted for demonstrating that the proposed method can achieve the state-of-the-art performance with smaller model size.

In this paper, we propose a novel network for super-resolution and achieve the state-of-the-art performance with limited parameters. Inspired by the previous methods, we use ResNet to learn the residual part of the input patches. In addition, we introduce an inception-like structure that helps to extract features and a weight sharing mechanism is utilized among these inception blocks. By cascading multi-scale filters with separate paths in a deep network, the proposed method can fully exploit the contextual information over large image regions. Besides, the residual learning module makes the training phase easy to converge. Extensive experiments demonstrate that the proposed method can achieve the same performance with fewer parameters compared with the previous state-of-the-art methods.

With the rapid rise of computer vision and driverless technology, vehicle model recognition plays a huge role in the common application and industry field. While fine-grained vehicle model recognition is often influenced by multi-level information, such as the image perspective, inter-feature similarity, vehicle details. Furthermore, pivotal regions extraction and fine-grained feature learning have become a vital obstacle to the fine-grained recognition of vehicle models. In this paper, we propose an iterative discrimination CNN (ID-CNN) based on selective multi-convolutional region (SMCR) feature extraction. The SMCR features, which consist of global and local SMCR features, are extracted from the original image with higher activation response value. As for ID-CNN, we use the global and local SMCR features iteratively to localize deep pivotal features and concatenate them together into a fully-connected fusion layer to predict the vehicle categories. We get better results and improve the accuracy to 91.8% on Stanford Cars-196 dataset and to 96.2% on CompCars dataset.

The common outage performance of an amplify‐and‐forward two‐hop two‐user channel is studied in the presence of multiple independent interferers at the destination. First, the exact integral form expression of the common outage probability is derived. Then, in order to decrease the computation complexity, a closed‐form approximation of the common outage probability is derived. Finally, the asymptotic analysis is performed based on the approximation expression. Numerical results demonstrate that the integral form of the common outage probability, the corresponding approximation and the asymptotic results match well with the Monte Carlo simulations.

This paper explores the rationale behind the Complete Voronoi Diagram (CVD) Localization, which is a computational geometry approach to the wireless network localization. Our work consists mainly of three parts. The first part focuses on the analysis of CVD's mathematical properties. We characterize CVD's central tendency as the mirror-image distribution and provide mathematical formula for its probability density function. We also provide a closed formula for the relationship between CVD's vertices, chords, and faces, the average chord length, and the average edge number of a CVD polygon. And, the expressions for the average overall and local positioning error are also provided. Based upon these findings, we show that the convergence speed for a CVD based localization scheme is quadratic, and the optimal time and space complexities are Θ(n2) and Θ(n), respectively. The second part proposes a novel approach, called Polling, which utilizes the concept of the Error Region, to further improve the accuracy. Polling, in theory, enables us to make use of the topology information with the quantity up to O(n4) provided by CVD for localization, while a conventional CVD scheme can use only O(1) such information. The third part, through simulations, shows how to use the quasi Analog-to-Digital Conversion (qADC) strategy to handle signal errors. Combined with Polling and qADC, a CVD scheme can provide a simple, robust, and powerful solution to the wireless network localization. Some of our findings and methods may also contribute to the field of computational geometry its own.