Hand gesture recognition (HGR) is a significant research area with applications in human-computer interaction, artificial intelligence, and more. In the early stage of development of HGR, there are high hardware costs and large usage requirements. To reduce the high cost expenditure and increase the application scenario, deep learning has played a crucial role. With the greater depth perception and more computing power, currently HGR is more about continuous recognition in space based on vedio. But in this article, it considers that there is a growing demand for lightweight networks with high precision for end-to-end HGR applications. In that, it still tends to recognize consecutive video frames and get results quickly. This paper introduces an enhanced network called YOLOv8-G2F, which is based on YOLOv8. It incorporates improved lightweight modules not only replace the traditional convolution module of the network's backbone and neck but also for the C2f module in YOLOv8. The network employs linear transformations, group convolution, and depthwise separable convolution to extract image information using simpler networks. Furthermore, model pruning is also used to further reduce model size and improve accuracy. The improved model achieved a recognition accuracy of 99.2% on the nus-ii gesture dataset with a model size of 2.33 MB. After extensive comparison and ablation experiments, YOLOv8-G2F demonstrated significant progress over existing algorithms.

In the control problems of multi-agent systems, collision avoidance is a fundamental safety requirement. One effective approach to ensure safety involves combining control barrier functions (CBFs) with quadratic programming (QP), where nominal control inputs are incorporated into QPs to achieve desired control objectives. Additionally, it is crucial to study the control performance of multi-agent systems to balance these objectives with control efforts. This work demonstrates that the performance index is closely related to the hyperparameters in the CBF-based QP controller, and the Bayesian optimization algorithm is used to optimize and improve performance. Firstly, a safe control approach is developed and a unified performance enhancement framework is established to optimize the performance index. Hyperparameters are then explored and categorized, introducing the concept of feasible hyperparameters to describe the attainability of control objectives. Subsequently, the constrained Bayesian optimization algorithm is employed to identify a set of feasible and optimal hyperparameters in a data-driven manner, even when the functional expressions of performance and constraints are unknown. Finally, experiments are conducted to demonstrate the feasibility of the proposed methods in multi-agent systems. Note to Practitioners—Both safety and optimality are of great importance in the control systems. The design and development of controllers for multi-agent systems are currently undergoing significant evolution. Academic researchers and industrial practitioners are actively refining controller designs to perform better in a variety of collaborative tasks. With practical applications in mind, there is a growing demand for control techniques capable of ensuring a safe operating environment while maintaining efficiency in energy consumption. Therefore, this paper aims to furnish practitioners and researchers with a safe control framework, facilitating the refinement of optimal control solutions for efficient collaboration among multiple agents.

Text-to-image models based on diffusion models are capable of generating highly realistic images from text descriptions. Nevertheless, in practical applications, the generated images frequently fail to fully satisfy user requirements regarding position and structure due to the absence of detailed location information and complex structural demands in the text descriptions. In order to improve the accuracy of the generated image in position and structure, the introduction of additional control conditions such as keypoint annotations or semantic segmentation has become an important research direction. This paper proposes a novel method based on a lightweight pre-trained diffusion model called CTIGEN-CDM. The model reduces computational costs by pruning the denoising network of the diffusion model and integrates control conditions into the denoising process through a gating mechanism to guide image generation. These control conditions encompass Canny edge detection, HED edge detection, depth maps, keypoints, and semantic segmentation. Experimental results reveal that CTIGEN-CDM possesses excellent generation quality and broad application potential. This method can generate high-quality images with precise positioning and structure while significantly saving computational resources, and it offers a promising new solution for text-to-image generation tasks.

Low-light image enhancement (LLIE) aims to restore low-light images to their normal-light counterparts with optimal global illumination distribution and clear local details. With the advancement of deep learning, deep learning-based methods have become the mainstream in the LLIE community. However, most deep learning-based method cannot yet fully exploit the global and local contextual information in the low-light image. In this paper, we introduce a dual-branch module to simultaneously restore global and local features from spatial and frequency domain. To fuse these multi-level features, we propose a perception module to perform feature interaction between global and local features via cross attention and self-gating. By integrating the two developed modules into a U-Net backbone, we present a global-local interaction network for LLIE. Furthermore, recent studies have shown that contrastive learning can be an effective paradigm for the LLIE task. However, previous works typically use semantically-inconsistent under-/over-exposed images as negative samples. These images are very dissimilar to the ground-truth and cannot provide sufficient regularization in contrastive learning. To address this limitation, we explore a practical multi-exposure progressive contrastive regularization framework for LLIE. With a customized sample generation, sample selection, and progressive learning strategy, our proposed framework progressively narrows down the solution space around the optimum, and helps to improve the performance of LLIE methods without additional inference overhead. Combining the proposed network and contrastive regularization, our proposed method achieves favorable results compared to state-of-the-art LLIE methods on benchmark datasets. Extensive experiments further demonstrate the generalization ability of our proposed method.

This paper studies the bipartite synchronization of signed networks with time-varying delays based on T-S fuzzy system, where the edges between nodes can be positive or negative. Assume that the signed graph of the network is structurally balanced. Firstly, the signed network system is described by T-S fuzzy model and then the control controller is used to control the network nodes, which can facilitate nodes to reach a synchronous state. Then some important lemmas and sufficient conditions are put forward to achieve bipartite synchronization of the signed networks. Finally, a numerical example is presented to certify the rationality of the theoretical results

Since the depth information of images facilitates the analysis of the spatial distance of objects in computer vision applications, it is necessary to protect the image depth information. Thus this article proposes a novel red-green-blue-depth (RGB-D) image protection algorithm, which is implemented with the finite-time synchronization (FTS) of neural networks (NNs) with proportional delays via the quantized intermittent control to derive the system synchronization criterion based on Lyapunov stability theory. The performance of RGB-D image protection depends on the synchronization error of the system by driving the system sequence to encrypt the RGB-D image and responding to the system sequence to decrypt the encrypted image. Subsequently, the validity of the proposed criteria is verified by simulation examples, and the practical application of RGB-D image protection is verified.

Images taken under low-light conditions suffer from poor visibility, color distortion, and graininess, all of which degrade the image quality and hamper the performance of downstream vision tasks, such as object detection and instance segmentation in the field of autonomous driving, making low-light enhancement an indispensable basic component of high-level visual tasks. Low-light enhancement aims to mitigate these issues, and has garnered extensive attention and research over several decades. The primary challenge in low-light image enhancement arises from the low signal-to-noise ratio caused by insufficient lighting. This challenge becomes even more pronounced in near-zero lux conditions, where noise overwhelms the available image information. Both traditional image signal processing pipeline and conventional low-light image enhancement methods struggle in such scenarios. Recently, deep neural networks have been used to address this challenge. These networks take unmodified RAW images as input and produce the enhanced sRGB images, forming a deep learning based image signal processing pipeline. However, most of these networks are computationally expensive and thus far from practical use. In this article, we propose a lightweight model called attentive dilated U-Net (ADU-Net) to tackle this issue. Our model incorporates several innovative designs, including an asymmetric U-shape architecture, dilated residual modules for feature extraction, and attentive fusion modules for feature fusion. The dilated residual modules provide strong representative capability, whereas the attentive fusion modules effectively leverage low-level texture information and high-level semantic information within the network. Both modules employ a lightweight design but offer significant performance gains. Extensive experiments demonstrate that our method is highly effective, achieving an excellent balance between image quality and computational complexity—that is, taking less than 4ms for a high-definition 4K image on a single GTX 1080Ti GPU and yet maintaining competitive visual quality. Furthermore, our method exhibits pleasing scalability and generalizability, highlighting its potential for widespread applicability.

The diffusion model has demonstrated impressive performance in image generation, but its potential for discriminative tasks such as instance segmentation remains unexplored. In this paper, we propose an Instance-aware Diffusion Implicit Process (IDIP) framework for instance segmentation based on boxes. During training, IDIP diffuses ground-truth boxes across various time steps, extracting corresponding Region of Interest (RoI) features. Dynamic convolution is then used to predict boxes and categories for each RoI, and the mask head generates masks from these predictions. During inference, IDIP iteratively refines randomly generated boxes with the denoising diffusion implicit model, while the mask head derives final masks from RoIs based on the refined boxes. Our method surpasses existing approaches on the COCO benchmark, requiring fewer training steps and less memory resources due to its dynamic design and instance-aware characteristic.

This paper addresses the state-dependent impulsive effects on robust exponential stability of quaternion-valued neural networks (QVNNs) with parametric uncertainties. In view of the noncommutativity of quaternion multiplication, we have to separate the concerned quaternion-valued models into four real-valued parts. Then, several assumptions ensuring every solution of the separated state-dependent impulsive neural networks intersects each of the discontinuous surface exactly once are proposed. In the meantime, by applying the B -equivalent method, the addressed state-dependent impulsive models are reduced to fixed-time ones, and the latter can be regarded as the comparative systems of the former. For the subsequent analysis, we proposed a novel norm inequality of block matrix, which can be utilized to analyze the same stability properties of the separated state-dependent impulsive models and the reduced ones efficaciously. Afterward, several sufficient conditions are well presented to guarantee the robust exponential stability of the origin of the considered models; it is worth mentioning that two cases of addressed models are analyzed concretely, that is, models with exponential stable continuous subsystems and destabilizing impulses, and models with unstable continuous subsystems and stabilizing impulses. In addition, an application case corresponding to the stability problem of models with unstable continuous subsystems and stabilizing impulses for state-dependent impulse control to robust exponential synchronization of QVNNs is considered summarily. Finally, some numerical examples are proffered to illustrate the effectiveness and correctness of the obtained results.

In this brief, considering the inertial term into first order neural networks(NNs), an inertial NN(INN) modeled by means of a differential inclusion is proposed for solving linear complementarity problem with P0matrix. Compared with existing NNs, the presence of the inertial term allows us to overcome some drawbacks of many NNs, which are constructed based on the steepest descent method, and this model is more convenient for exploring different optimal solution. It is proved that the proposed NN is stable in the sense of Lyapunov and any equilibrium of our NN is the optimal solution of LCP with P0matrix. Simulation results on two numerical examples show the effectiveness and performance of the proposed neural network.

In this brief, based on the method of penalty functions, a recurrent neural network (NN) modeled by means of a differential inclusion is proposed for solving the bilevel linear programming problem (BLPP). Compared with the existing NNs for BLPP, the model has the least number of state variables and simple structure. Using nonsmooth analysis, the theory of differential inclusions, and Lyapunov-like method, the equilibrium point sequence of the proposed NNs can approximately converge to an optimal solution of BLPP under certain conditions. Finally, the numerical simulations of a supply chain distribution model have shown excellent performance of the proposed recurrent NNs.