Vibration energy harvesting is a promising solution for powering battery-free IoT systems; however, the instability of ambient vibrations presents significant challenges, such as limited harvested energy, intermittent power supply, and poor adaptability to various applications. To address these challenges, this paper proposes ViPSN2.0, a modular and reconfigurable IoT platform that supports multiple vibration energy harvesters (piezoelectric, electromagnetic, and triboelectric) and accommodates sensing tasks with varying application requirements through standardized hot-swappable interfaces. ViPSN 2.0 incorporates an energyindication power management framework tailored to various application demands, including light-duty discrete sampling, heavyduty high-power sensing, and complex-duty streaming tasks, thereby effectively managing fluctuating energy availability. The platform’s versatility and robustness are validated through three representative applications: ViPSN-Beacon, using an ultra-lowcost structural PZT (ϕ35 mm, <0.002 $) to enable a BLE advertisement from a single transient fingertip press with 100 m line of sight; ViPSN-LoRa, supporting wireless communication powered by wave vibrations in actual marine environments (Bohai Bay) with per-uplink task energy compatible with kilometer-scale field links; and ViPSN-Cam, enabling intermittent image capture and wireless transfer, delivering one frame approximately every 15 s under typical conditions. Experimental results demonstrate that ViPSN 2.0 can reliably meet a wide range of requirements in practical battery-free IoT deployments under energy-constrained conditions.

Human-motion energy harvesting is emerging as a promising solution for wearable electronics and devices, offering a sustainable power source that extends operational longevity and enhances durability. However, current techniques and prototypes have yet to achieve fully interactive, battery-free functionality. This paper presents a battery-free interactive gaming system powered by energy harvested from transient fingertip motion. To ensure the reactivity, interactivity, and stability of the fingertip motion harvester (FMH), we employ a multistable structure. The FMH unit provides a reliable energy solution by utilizing precharged potential energy within dynamically varying potential wells. Additionally, the integration of a bistable screen design facilitates seamless gaming experiences, decouples game logic from user interface mechanics, and ensures rapid system recovery after power interruptions. Beyond advancing fundamental research, this work pioneers a practical battery-free interaction paradigm based on fingertip motion, with potential for broader battery-free user interfaces and low-power interactive systems.

This demonstration showcases a battery-free wireless keyboard that utilizes the kinetic energy generated from key presses to generate electrical power. Each key incorporates a Quasi-Static Toggling harvester, which employs potential energy pre-charging to ensure a consistently reliable energy output. Extensive practical testing has confirmed that this keyboard exhibits responsiveness and low latency comparable to traditional wireless keyboards. This study represents a significant improvement over previous battery-free IoT applications that often compromised service quality, as it offers a stable energy-harvesting mechanism and provides a dependable framework for designing battery-free devices.

Over the last few years, deep learning based approaches have achieved outstanding improvements in natural image matting. Many of these methods can generate visually plausible alpha estimations, but typically yield blurry structures or textures in the semitransparent area. This is due to the local ambiguity of transparent objects. One possible solution is to leverage the far-surrounding information to estimate the local opacity. Traditional affinity-based methods often suffer from the high computational complexity, which are not suitable for high resolution alpha estimation. Inspired by affinity-based method and the successes of contextual attention in inpainting, we develop a novel end-to-end approach for natural image matting with a guided contextual attention module, which is specifically designed for image matting. Guided contextual attention module directly propagates high-level opacity information globally based on the learned low-level affinity. The proposed method can mimic information flow of affinity-based methods and utilize rich features learned by deep neural networks simultaneously. Experiment results on Composition-1k testing set and alphamatting.com benchmark dataset demonstrate that our method outperforms state-of-the-art approaches in natural image matting. Code and models are available at https://github.com/Yaoyi-Li/GCA-Matting.

Recently, significant progress has been achieved in deep image matting. Most of the classical image matting methods are time-consuming and require an ideal trimap which is difficult to attain in practice. An efficient image matting method based on a weakly annotated mask is in demand for mobile applications. In this paper, we propose a novel method called Inductive Guided Filter, which tackles the real-time general image matting task with weakly annotated masks on mobile devices. The Inductive Guided Filter exploits the gradient prior implicit in Guided Filter to reduce the computational burden tremendously in a deep learning manner. The use of Gabor loss is also proposed for complicated textures in image matting. Moreover, we create an image matting dataset MAT-2793 with a variety of foreground objects. Experimental results demonstrate that our proposed method massively reduces running time with robust accuracy.

Much recently, an internal model approach from output regulation theory has been adopted to solve the speed tracking control problem of the permanent magnet synchronous motor (PMSM) system on simulation level. A striking advantage of this approach is that it can achieve multiple goals including trajectory tracking, disturbance rejection, and robustness simultaneously. This article further studies a position tracking control problem of the PMSM system under nonlinear load torque disturbance. A nonlinear internal model based output feedback controller is proposed, which can achieve exact position tracking and allow certain parameter uncertainties. Besides simulation results, a real-time experimental setup is built and experimental results are provided to illustrate the effectiveness of the proposed controller. It is worth mentioning that the proposed controller can lead to a high precision position tracking performance under nonlinear load torque disturbance.

Recent studies show significant progress in image-to-image translation task, especially facilitated by Generative Adversarial Networks. They can synthesize highly realistic images and alter the attribute labels for the images. However, these works employ attribute vectors to specify the target domain which diminishes image-level attribute diversity. In this paper, we propose a novel model formulating disentangled representations by projecting images to latent units, grouped feature channels of Convolutional Neural Network, to disassemble the information between different attributes. Thanks to disentangled representation, we can transfer attributes according to the attribute labels and moreover retain the diversity beyond the labels, namely, the styles inside each image. This is achieved by specifying some attributes and swapping the corresponding latent units to “swap” the attributes appearance, or applying channel-wise interpolation to blend different attributes. To verify the motivation of our proposed model, we train and evaluate our model on face dataset CelebA. Furthermore, the evaluation of another facial expression dataset RaFD demonstrates the generalizability of our proposed model.

Image inpainting, which aims to fill the missing holes of the images, is a challenging task because the holes may contain complicated structures or different possible layouts. Deep learning methods have shown promising performance in image inpainting but still, suffer from generating poor-structured artifacts when the holes are large and irregular. Some existing methods use edge inpainting to help image inpainting, with binary edge map obtained from image gradient. However, by only using the binary edge map, these methods discard the rich information in image gradient and thus leave some critical issues (e.g. , color discrepancy) unattended. In this paper, we propose Gradient Augmented Inpainting Network (GAIN), which uses image gradient information instead of edge information to facilitate image inpainting. Specifically, we formulate a multi-task learning framework which performs image inpainting and gradient inpainting simultaneously. A novel GAI-Block is designed to encourage the information fusion between the image feature map and the gradient feature map. Moreover, gradient information is also used to determine the filling priority, which can guide the network to construct more plausible semantic structures for the holes. Experimental results on public datasets CelebA-HQ and Places2 show that our proposed method outperforms state-of-the-art methods quantitatively and qualitatively.

Hashing for similarity search in large scale data has become an increasingly popular technique. K-means Hashing (KMH) has been proven effective because of the benefits of adaptive k-means quantization. However, KMH is a batch-based learning model requiring high time and storage complexities, which makes it hard to load large scale data into memory to train and deal with streaming data. To address this problem, in this paper we propose an online hashing method using Self-Organizing Map (SOM) algorithm, named as Online Self-Organizing Hashing (SOH). Specifically, we map the training data to an affinity preserving hyper-cube with each vertex assigned a binary code using a SOM alike algorithm. After training, a new data point is quantized into a vertex of the hyper-cube and encoded into related binary code. Experimental results demonstrate that SOH has better or comparable retrieval performance to various state-of-the-art hashing methods while simultaneously requiring rather low computational complexity and storage space.

Spectral clustering is one of the most popular clustering approaches with the capability to handle some challenging clustering problems. Only a little work of spectral clustering focuses on the explicit linear map which can be viewed as the distance metric learning. In practice, the selection of the affinity matrix exhibits a tremendous impact on the unsupervised learning. In this paper, we propose a novel method, dubbed Adaptive Affinity Matrix (AdaAM), to learn an adaptive affinity matrix and derive a distance metric. We assume the affinity matrix to be positive semidefinite with ability to quantify the pairwise dissimilarity. Our method is based on posing the optimization of objective function as a spectral decomposition problem. The provided matrix can be regarded as the optimal representation of pairwise relationship on the manifold. Extensive experiments on a number of image data sets show the effectiveness and efficiency of AdaAM.

We propose a novel method for feature description used for image matching in this paper. Our method is inspired by the autoencoder, an artificial neural network designed for learning efficient codings. Sparse and orthogonal constraints are imposed on the autoencoder and make it a highly discriminative descriptor. It is shown that the proposed descriptor is not only invariant to geometric and photometric transformations (such as viewpoint change, intensity change, noise, image blur and JPEG compression), but also highly efficient. We compare it with existing state-of-the-art descriptors on standard benchmark datasets, the experimental results show that our LSOD method yields better performance both in accuracy and efficiency.