检索结果-内蒙古大学图书馆

Unsupervised Cross-Domain 3D Human Pose Estimation via Pseudo-Label-Guided Global Transforms

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Jingjing Wang, Zhiyong Fan, Xinyu Dadashzadeh, Amirhossein Liu, Honghai Mirmehdi, Majid School of Computer Science University of Bristol United Kingdom State Key Laboratory of Robotics and Systems Harbin Institute of Technology Shenzhen China School of Aerospace Engineering Xiamen University China

Existing 3D human pose estimation methods often suffer in performance, when applied to cross-scenario inference, due to domain shifts in characteristics such as camera viewpoint, position, posture, and body size. Among these factors, camera viewpoints and locations have been shown to contribute significantly to the domain gap by influencing the global positions of human poses. To address this, we propose a novel framework that explicitly conducts global transformations between pose positions in the camera coordinate systems of source and target domains. We start with a Pseudo-Label Generation Module that is applied to the 2D poses of the target dataset to generate pseudo-3D poses. Then, a Global Transformation Module leverages a human-centered coordinate system as a novel bridging mechanism to seamlessly align the positional orientations of poses across disparate domains, ensuring consistent spatial referencing. To further enhance generalization, a Pose Augmentor is incorporated to address variations in human posture and body size. This process is iterative, allowing refined pseudo-labels to progressively improve guidance for domain adaptation. Our method is evaluated on various cross-dataset benchmarks, including Human3.6M, MPI-INF-3DHP, and 3DPW. The proposed method outperforms state-of-the-art approaches and even outperforms the target-trained model. Copyright © 2025, The Authors. All rights reserved.

关键词： Three dimensional computer graphics

OUTLIER SYNTHESIS VIA HAMILTONIAN MONTE CARLO FOR OUT-OF-DISTRIBUTION DETECTION

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Hengzhuang Zhang, Teng National Engineering Research Center for Big Data Technology and System Service Computing Technology and Systems Laboratory Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Out-of-distribution (OOD) detection is crucial for developing trustworthy and reliable machine learning systems. Recent advances in training with auxiliary OOD data demonstrate efficacy in enhancing detection capabilities. Nonetheless, these methods heavily rely on acquiring a large pool of high-quality natural outliers. Some prior methods try to alleviate this problem by synthesizing virtual outliers but suffer from either poor quality or high cost due to the monotonous sampling strategy and the heavy-parameterized generative models. In this paper, we overcome all these problems by proposing the Hamiltonian Monte Carlo Outlier Synthesis (HamOS) framework, which views the synthesis process as sampling from Markov chains. Based solely on the in-distribution data, the Markov chains can extensively traverse the feature space and generate diverse and representative outliers, hence exposing the model to miscellaneous potential OOD scenarios. The Hamiltonian Monte Carlo with sampling acceptance rate almost close to 1 also makes our framework enjoy great efficiency. By empirically competing with SOTA baselines on both standard and large-scale benchmarks, we verify the efficacy and efficiency of our proposed HamOS. Our code is available at: https://***/Fir-lat/HamOS_OOD. © 2025, CC BY.

关键词： Markov chains

Constrained Coding for Magnetization Transition Noise of Ultra-High Density Magnetic Storage

学校读者我要写书评

暂无评论

Tien Tzu Hsueh Pao/Acta Electronica Sinica 2025年第2期53卷 483-492页

作者： Luo, Ke Li, Wei Jian, Yu-Gen Gao, Hong-Yu Zhang, Ke-Zheng Liao, Yan-Zhe Wu, Yu-Fei Chen, Jin-Cai Lu, Ping Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Hubei Wuhan430074 China School of Computer Science and Technology Huazhong University of Science and Technology Hubei Wuhan430074 China Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China Huazhong University of Science and Technology Hubei Wuhan430074 China

As the recording density of magnetic storage increases, the recording bit spacing decreases and the magnetization transition noise increases significantly, which greatly affects the quality of the readback signal. To mitigate the interference of magnetization transition noise problem among recording patterns in ultra-high density magnetic storage systems, the maximum transition run (MTR) constraint code MTR(j= 1), which limits the continuous transition, is proposed to effectively suppress the magnetization transition noise compared with the constraint codes MTR(j= 2) and MTR(j= 3), which allow continuous transitions. We investigate the detection effect of the readback signal experimentally. When the signal-to-noise ratio is 12 dB, the detection bit error rate (BER) of MTR(j= 1) is reduced by about 30% and 60% relatively compared with MTR(j= 2) and MTR(j= 3), respectively. We confirmed that the MTR(j= 1) constrained coding that forbids continuous transitions can achieve higher data detection reliability. © 2025 Chinese Institute of Electronics. All rights reserved.

关键词： MRAM devices

Beyond Degradation Conditions: All-in-One Image Restoration via HOG Transformers

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wu, Jiawei Yang, Zhifei Wang, Zhe Jin, Zhi School of Intelligent Systems Engineering Sun Yat-sen University Shenzhen Campus Guangdong China School of Computer Science Peking University China Guangdong Provincial Key Laboratory of Fire Science and Technology Guangzhou China

All-in-one image restoration, which aims to address diverse degradations within a unified framework, is critical for practical applications. However, existing methods rely on predicting and integrating degradation conditions, which can misactivate degradation-specific features in complex scenarios, limiting their restoration performance. To address this issue, we propose a novel all-in-one image restoration framework guided by Histograms of Oriented Gradients (HOG), named HOGformer. By leveraging the degradation-discriminative capability of HOG descriptors, HOGformer employs a dynamic self-attention mechanism that adaptively attends to long-range spatial dependencies based on degradation-aware HOG cues. To enhance the degradation sensitivity of attention inputs, we design a HOG-guided local dynamic-range convolution module that captures long-range degradation similarities while maintaining awareness of global structural information. Furthermore, we propose a dynamic interaction feed-forward module, efficiently increasing the model capacity to adapt to different degradations through channel–spatial interactions. Extensive experiments across diverse benchmarks, including adverse weather and natural degradations, demonstrate that HOGformer achieves state-of-the-art performance and generalizes effectively to complex real-world degradations. Code is available at https://***/Fire-friend/HOGformer. Copyright © 2025, The Authors. All rights reserved.

关键词： Mapping

Laser-patterned gold-leaf/WPU conductive films for flexible electronics

学校读者我要写书评

暂无评论

Sensors and Actuators A: Physical 2025年 391卷

作者： Sheng, Bin Zhou, Jingyu Wen, Ziqi Tang, Lei Zhang, Dawei School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China Shanghai Key Laboratory of Modern Optical Systems Engineering Research Center of Optical Instruments and Systems Shanghai200093 China

Gold is typically used as conductive layers in wearable electronics because of their good conductivity and chemical stability;however, the weak adhesion between gold films and flexible substrates is a persistent engineering issue. In this report, we introduce a convenient and unique process for preparing flexible conductive films compounded with traditional gold leaf of 110-nm thickness and waterborne polyurethane (WPU) film, which meet the highest ASTM class standard of 5B and has excellent adhesion strength (not less than 440 N/m) between the gold leaf and the WPU film. The resulting gold-leaf/WPU conductive film (GWCF) exhibits excellent conductivity (1.14 ×107 S/m) and a sheet resistance of 0.8Ω/sq and a 50 % stretchable working range, GF (61.3). The average adhesion strength of the gold leaf on the WPU film (prepared via in-situ polymerization) was 1257 ± 50 N/m. The sensor withstood 2000 finger frictions and 500 contact frictions, maintaining stable resistance without significant changes, and was successfully developed into strain sensors for gesture recognition. Furthermore, rear-side laser ablation method was used for high-precision patterning of gold leaf (with minimum line width of 50 µm and minimum line pitch of 25 µm), resulting various flexible electrodes of shapes. The flexible humidity sensor with interdigital electrode of GWCF and graphene oxide shows high sensitivity, repeatability, and stability under bending;and GWCF-based flexible circuits offer high transparency, waterproofing, and stable deformation, with applications in wearables and fabric-integrated LED circuits. Additionally, a flexible smart remote controller using GWCF was developed for omnidirectional control of a smart vehicle via Bluetooth, enhancing human-machine interaction. In summary, this study presents an easy and cost-effective approach to fabricating flexible gold electrodes with great potential for flexible electronics applications. © 2025 Elsevier B.V.

关键词： Flexible electronics

Stealthy Attacks on Sampled-Data Control and Encryption-Based Countermeasures

学校读者我要写书评

暂无评论

IEEE Transactions on Automatic Control 2025年

作者： Shang, Jun Li, Yuzhe Chen, Tongwen Tongji University Department of Control Science and Engineering Shanghai Institute of Intelligent Science and Technology National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Shanghai200092 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110004 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 1H9 Canada

This paper investigates stealthy attacks on sampled-data control systems, where a continuous process is sampled periodically, and the resultant discrete output and control signals are transmitted through dual channels in wireless communication networks. Acknowledging the vulnerability of these transmitted data to cyber threats, we analyze two types of stealthy attacks that compromise either one or both channels. We explicitly present the necessary and sufficient conditions for the existence of stealthy single-channel attacks. To mitigate these security risks, we implement encryption-based countermeasures, including linear time-invariant and periodic encryption methods. We detail sufficient conditions under which these encryption strategies effectively thwart single- and dual-channel stealthy attacks. The effectiveness of these approaches and the theoretical findings are demonstrated through numerical simulations. © 1963-2012 IEEE.

关键词： Cyber attacks

Adaptive Incremental Broad Learning System Based on Interval Type-2 Fuzzy Set with Automatic Determination of Hyperparameters

学校读者我要写书评

暂无评论

IEEE Transactions on Fuzzy systems 2025年

作者： Wu, Haijie Lin, Weiwei Chen, Yuehong Shi, Fang Shen, Wangbo Chen, C. L. Philip South China University of Technology School of Computer Science and Engineering Guangzhou510006 China Pengcheng Laboratory Shenzhen518066 China Guangdong Polytechnic Normal University School of Mathematics and Systems Science Guangzhou510665 China South China Agricultural University College of Mathematics and Informatics Guangzhou510642 China South China University of Technology School of Computer Science and Engineering Guangzhou511442 China

The fuzzy broad learning system (FBLS) has received increasing attention due to its ability to quickly train from broad learning systems (BLS) and interpretability with fuzzy inference. However, the randomness of BLS brings instability to the training performance of the model, so the hyperparameters of the model are crucial for its performance. Currently, many FBLS use grid search to determine hyperparameters. However, grid search brings longer search time and the parameters obtained have randomness, which may not necessarily be the optimal hyperparameters. In response to these challenges, this paper proposes a fuzzy broad learning system with automatic determination of hyperparameters (ADHFBLS). We construct a novel FBLS based on the interval type-2 fuzzy set and design an incremental learning algorithm for rules and enhancement nodes to support rapid model expansion. Meanwhile, a heuristic hyperparameter automatic optimization algorithm is designed to overcome the randomness and long optimization time of grid search. Experiments have shown that ADHFBLS has higher accuracy and shorter model tuning time compared to some state-of-the-art models based on FBLS. © 1993-2012 IEEE.

关键词： Adversarial machine learning

UNeLF: Unconstrained Neural Light Field for Self-Supervised Angular Super-Resolution

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Zhao, Mingyuan Sheng, Hao Chen, Rongshan Cong, Ruixuan Cui, Zhenglong Yang, Da Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Data Science and Intelligent Computing Laboratory Hangzhou International Innovation Institute Hangzhou311115 China Macao Polytechnic University Faculty of Applied Sciences 999078 China

Compared to supervised learning methods, self-supervised learning methods address the domain gap problem between light field (LF) datasets collected under varying acquisition conditions, which typically leads to decreased performance when differences exist in the distribution between the training and test sets. However, current self-supervised light field angular super-resolution (LFASR) techniques primarily focus on exploiting discrete spatial-angular features while neglecting continuous LF information. In contrast to previous work, we propose a self-supervised unconstrained neural light field (UNeLF) to continuously represent LF for LFASR. Specifically, any LF can be described as the camera pose for each sub-aperture image (SAI) and the two-plane that captures these SAIs. To describe the former, we introduce a SAIs-dependent pose optimization method to solve the issue that arises from the narrow baseline of most LF data, which hinders robust camera pose estimation. This mechanism reduces the number of trainable camera parameters from a quadratic to a constant scale, thereby alleviating the complexity of joint optimization. For the latter, we propose a novel adaptive two-plane parameterization strategy to determine the two-plane that captures these SAIs, facilitating refocusing. Finally, we jointly optimize the camera parameters, near-far planes and neural light field, efficiently mapping each adaptive two-plane parameterized ray to its correspondence color in a continuous manner. Comprehensive experiments demonstrate that UNeLF achieves faster training and inference with fewer computational resources while exhibiting superior performance on both synthetic and real-world datasets. © 1991-2012 IEEE.

关键词： Self-supervised learning

SwimVG: Step-wise Multimodal Fusion and Adaption for Visual Grounding

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Shi, Liangtao Liu, Ting Hu, Xiantao Hu, Yue Yin, Quanjun Hong, Richang Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei230009 China Ministry of Education and School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China School of systems engineering National University of Defense Technology Hunan Province Changsha410073 China Department of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210014 China

Visual grounding aims to ground an image region through natural language, which heavily relies on cross-modal alignment. Most existing methods transfer visual/linguistic knowledge separately by fully fine-tuning uni-modal pre-trained models, followed by a simple stack of visual-language transformers for multimodal fusion. However, these approaches not only limit adequate interaction between visual and linguistic contexts, but also incur significant computational costs. Therefore, to address these issues, we explore a step-wise multimodal fusion and adaption framework, namely SwimVG. Specifically, SwimVG proposes step-wise multimodal prompts (Swip) and cross-modal interactive adapters (CIA) for visual grounding, replacing the cumbersome transformer stacks for multimodal fusion. Swip can improve the alignment between the vision and language representations step by step, in a token-level fusion manner. In addition, weight-level CIA further promotes multimodal fusion by cross-modal interaction. Swip and CIA are both parameter-efficient paradigms, and they fuse the cross-modal features from shallow to deep layers gradually. Experimental results on four widely-used benchmarks demonstrate that SwimVG achieves remarkable abilities and considerable benefits in terms of efficiency. Our code is available at https://***/liuting20/SwimVG. Copyright © 2025, The Authors. All rights reserved.

关键词： Visual languages