This paper presents WeavePrint, a parametric and multi-material additive manufacturing method for woven-like structures. By fusing traditional weaving logic with computational generation, WeavePrint overcomes limitations in pattern programmability, mechanical tunability, and build size. A parametric generator creates plain, twill, satin, and image-based jacquard patterns, while supporting curved-surface mapping and continuous vertical roll-to-roll printing for scalable production. Systematic tensile and compression tests quantify how overlap length, filament width, and multi-material combinations influence inter-layer adhesion and global mechanics. We define four motion primitives: bending, twisting, curved extension-contraction, and hinged extension-contraction, implemented through straight, diagonal, and curved weaves to produce predictable deformations. Demonstrations in wearable supports, robotic components, and rehabilitation devices highlight its broad potential in human-computer interaction. By unifying parametric modeling with multi-material continuous fabrication, WeavePrint provides a scalable route to programmable, anisotropic, and dynamically responsive interactive fabrics.

Multimodal 3D segmentation involves a significant number of 3D convolution operations, which requires substantial computational resources and high-performance computing devices in MRI multimodal brain tumor segmentation. The key challenge in multimodal 3D segmentation is how to minimize network computational load while maintaining high accuracy. To address the issue, a novel lightweight parameter aggregation network (SuperLightNet) is proposed to realize the efficient encoder and decoder for the high accurate and low computation. A random multiview drop encoder is designed to learn the spatial structure of multimodal images through a random multi-view approach for solving the high computational time complexity that has arisen in recent years with methods relying on transformers and Mamba. A learnable residual skip decoder is designed to incorporate learnable residual and group skip weights for addressing the reduced computational efficiency caused by the use of overly heavy convolution and deconvolution decoders. Experimental results demonstrate that the proposed method achieves a leading reduction in parameter count by 95.59%, the 96.78% improvement in computational efficiency, the 96.86% enhancement in memory access performance, and the average performance gain of 0.21% on the BraTS2019 and BraTS2021 datasets in comparison with the state-of-the-art methods. Code is available at https://github.com/WTU-MIS-Laboratory/SuperLightNet.

The ViT models have a large number of parameters and intensive matrix computations, making it challenging to deploy on resource-constrained FPGAs for acceleration. In this paper, we propose an end-to-end quantized ViT accelerator that adopts a multi-kernel architecture and a time-multiplexed scheduling strategy. We implement customized hardware for key operations in ViTs, enabling efficient resource utilization and memory-friendly features. Experiments show that compared to Edge-MoE, our accelerator achieves an 8.64× improvement in energy efficiency. Meanwhile, hardware resource consumption is significantly reduced, making it more suitable for resource-constrained FPGAs.

Vision Transformer (ViT) has achieved great success in computer vision tasks, and FPGA-based ViT inference acceleration has recently gained widespread attention. However, the massive number of parameters and intensive matrix computations make it challenging to accelerate ViT models on resource-constrained FPGAs. To address this challenge, prior works have explored ViT quantization and approximate implementations of non-linear operations, but significant hardware resource consumption and potential performance optimization opportunities remain. In this paper, we propose an end-to-end quantized ViT accelerator, EQViTA. Its multi-kernel architecture and time-multiplexed scheduling strategy enable efficient resource utilization and memory-friendly features. We customize designs for the key operators of ViTs. First, we compress the model using INT4 quantization and implement the dataflow of the quantized model through resource-optimized dequantization. Second, we eliminate the convolution hardware module by using the convolution-to-linear mapping, thereby reducing resource usage. Finally, we achieve low-cost and highly parallel acceleration of self-attention and linear transformations through efficient exponential approximation for softmax and an adaptive linear transformation engine. Experiments on the Xilinx ZCU106 FPGA show that compared with state-of-the-art works, EQViTA achieves$1.03 \times$to$8.64 \times$improvements in energy efficiency and$1.14 \times$to$18.6 \times$improvements in normalized throughput. Meanwhile, EQViTA significantly reduces LUT, FF, BRAM, and DSP resource consumption, making it more suitable for resource-constrained FPGAs. Compared to the full-precision DeiT-Tiny model implemented with PyTorch, the INT4 quantized model deployed on EQViTA exhibits a 5.93 % accuracy drop.

As emerging visual sensors, event cameras are gaining attention for their excellent temporal resolution, low power consumption and extremely high dynamic range. Some studies have explored Field Programmable Gate Array (FPGA)-based systems for edge event-driven Multi-Object Tracking (MOT) tasks, which aim to achieve high real-time performance and tracking accuracy with strict resource and power constraints. Among these FPGA-based systems, the per-event processing systems can effectively utilize event cameras' high temporal resolution and asynchronous nature. To address the performance and resource overhead issues in per-event processing systems, this paper presents the Boundary-Movement-based Multi-Object Tracking (BMMOT) event-driven system for high-performance and resource-efficient MOT tasks while keeping reasonable power consumption and accuracy. BMMOT employs a straightforward boundary-movement-based tracking mechanism for tracker design. Additionally, a tracker lifecycle management strategy and a tracker merging strategy, based on concise motion trend criteria, are adopted to ensure the system functions properly. Effective BMMOT circuit designs are also proposed. The efficiency of BMMOT is validated by multiple academic and real-world datasets captured by different cameras. BMMOT implemented on an AMD ZYNQ FPGA has an event processing latency of 19.6-$137.2 ~\text{ns} /$event and can process up to 51 million events per second with a power consumption of less than 2.71 W. BMMOT keeps good accuracy$(52.1 \%-79.4 \%)$for the datasets. Under a similar tracking system configuration, higher performance is obtained while almost all block RAMs,$16.4-41.0 \%$look-up tables, and$64.5-78.7 \%$flip-flops can be saved compared to existing work.

Storytelling plays a crucial role in the development of children’s comprehensive abilities. This paper presents an innovative AI drawing game designed to enhance children’s capabilities in using metaphors and storytelling. The game employs a unique approach, allowing children to capture scenes or objects from the real world using a built-in camera and describe them via voice input, which then generates corresponding images on the interface. The AI drawing module of the game, developed based on the LCM model, converts children’s descriptions into images in real time, offering a dynamic and almost instantaneous storytelling experience. This study explores the impact of the game on children’s creativity and narrative skills, presenting a novel way of integrating AI into child development.

Intelligent wearable systems have been widely used in health monitoring, motion tracking, and engineering safety. However, the single function of current wearable systems cannot satisfy the requirements of complex scenarios, and the wearable systems cannot establish a relationship with the virtual 3D visualization platform. To address these issues, this paper proposes a novel intelligent wearable system with motion and emotion recognition. Multiple sensors are integrated into the system to collect motion and emotion information. In order to achieve accurate classification and recognition of multiple sensor information, we propose a novel human action recognition network called the three-branch spatial-temporal feature extraction network (TB-SFENet), which can obtain more robust features and achieve an accuracy of 97.04% on the UCI-HAR dataset and 92.68% on the UniMiB SHAR dataset. To establish the relationship between the real entity and virtual space, we use digital twin (DT) technology to establish the 3D display DT platform. The platform enables real-time information interaction, such as activity, emotion, location, and monitoring information. Additionally, we establish the TGAM electroencephalogram emotion classification (TEEC) dataset, which contains 120,000 pieces of data, for the proposed system. Experimental results indicate that the proposed system realizes virtual reality information interaction between the personal digital human and actual person based on the intelligent wearable system, which has great potential for applications in intelligent healthcare, virtual reality, and other fields.

Adaptive voltage and frequency scaling (AVFS) technology adjusts the supply voltage and clock frequency based on the actual operating conditions of the circuit. It can significantly improve performance or reduce the power consumption of the device. Existing online field-programmable gate array (FPGA) AVFS solutions have relatively low adjustment efficiency. Many existing solutions rely on offline steps, which do not consider the runtime operating conditions. This article proposes a complete FPGA AVFS solution, which includes a versatile self-checking timing monitor (SCTM) with small resource overhead, efficient AVFS algorithms without any offline steps, and user-friendly comprehensive automation software. Compared with existing online solutions, the proposed solution improves scaling efficiency by reducing the number of configuration times for the clock generation unit. The effectiveness of the solution is evaluated by a set of pubic benchmarks. Experimental results indicate that it can set an appropriate voltage–frequency operating point for the application circuit within dozens of milliseconds. For power-oriented adjustment, the proposed solution can save power ranging from 33.93% to 43.46%, while keeping the frequency not slower than the one reported by the static timing analysis (STA). For performance-oriented adjustment, it can achieve a performance improvement ranging from 60.26% to 101.90% at the nominal voltage.