arXiv subjects

Yanyan Yang

Publications and source records attributed to Yanyan Yang.

7 recordsLinked to original sources

arXiv2025

Magnetization switching by current in an elemental ferromagnetic single layer

Current-induced magnetization switching, a fundamental phenomenon related to spin-transport of electrons, enables non-voltaic and fast information write, facilitating applications in low-power memory and logic devices. However, magnetization switching by spin-orbit torques is usually attributed to current flowing in the nonmagnetic metal layer of multilayers or in magnetic alloys with heavy elements. Here, we report perpendicular magnetization switching induced by current flowing in an elemental ferromagnet nickel single layer. This prototype structure demonstrates that current-induced magnetization switching is a general phenomenon of magnet. The results suggest that the current induces an effective transverse magnetic field with an out-of-plane component leading to the magnetization switching, different to the conventional spin-orbit torques. Our work opens the new insight and reveals the intrinsic mechanism of current-induced torques.

cond-mat.mtrl-sci↗

arXiv2025

Hierarchical Mask-Enhanced Dual Reconstruction Network for Few-Shot Fine-Grained Image Classification

Few-shot fine-grained image classification (FS-FGIC) is challenging as it requires distinguishing visually similar subclasses with extremely limited labeled examples. Existing methods suffer from critical limitations: metric-based methods lose spatial information and misalign local features, while reconstruction-based methods underuse hierarchical feature information and lack selective focus on discriminative key regions. We propose the Hierarchical Mask-enhanced Dual Reconstruction Network (HMDRN), integrating dual-layer feature reconstruction with mask-enhanced feature processing. HMDRN leverages complementary visual information from different network hierarchies via learnable weights, balancing high-level semantic representations with mid-level structural details. It incorporates a spatial binary mask-enhanced transformer module that selectively enhances discriminative regions while filtering background noise. On three fine-grained datasets, HMDRN consistently outperforms state-of-the-art methods with both Conv-4 and ResNet-12 backbones. Ablation studies validate each component's effectiveness, showing dual-layer reconstruction enhances inter-class discrimination while mask-enhanced transformation reduces intra-class variations.

cs.CV↗

arXiv2024

Guided Diffusion for Fast Inverse Design of Density-based Mechanical Metamaterials

Mechanical metamaterial is a synthetic material that can possess extraordinary physical characteristics, such as abnormal elasticity, stiffness, and stability, by carefully designing its internal structure. To make metamaterials contain delicate local structures with unique mechanical properties, it is a potential method to represent them through high-resolution voxels. However, it brings a substantial computational burden. To this end, this paper proposes a fast inverse design method, whose core is an advanced deep generative AI algorithm, to generate voxel-based mechanical metamaterials. Specifically, we use the self-conditioned diffusion model, capable of generating a microstructure with a resolution of $128^3$ to approach the specified homogenized tensor matrix in just 3 seconds. Accordingly, this rapid reverse design tool facilitates the exploration of extreme metamaterials, the sequence interpolation in metamaterials, and the generation of diverse microstructures for multi-scale design. This flexible and adaptive generative tool is of great value in structural engineering or other mechanical systems and can stimulate more subsequent research.

cs.CE↗

arXiv2022

Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granularity

Chinese spelling check (CSC) is a fundamental NLP task that detects and corrects spelling errors in Chinese texts. As most of these spelling errors are caused by phonetic similarity, effectively modeling the pronunciation of Chinese characters is a key factor for CSC. In this paper, we consider introducing an auxiliary task of Chinese pronunciation prediction (CPP) to improve CSC, and, for the first time, systematically discuss the adaptivity and granularity of this auxiliary task. We propose SCOPE which builds on top of a shared encoder two parallel decoders, one for the primary CSC task and the other for a fine-grained auxiliary CPP task, with a novel adaptive weighting scheme to balance the two tasks. In addition, we design a delicate iterative correction strategy for further improvements during inference. Empirical evaluation shows that SCOPE achieves new state-of-the-art on three CSC benchmarks, demonstrating the effectiveness and superiority of the auxiliary CPP task. Comprehensive ablation studies further verify the positive effects of adaptivity and granularity of the task. Code and data used in this paper are publicly available at https://github.com/jiahaozhenbang/SCOPE.

cs.CL↗

arXiv2019

Multi-View Region Adaptive Multi-temporal DMM and RGB Action Recognition

Human action recognition remains an important yet challenging task. This work proposes a novel action recognition system. It uses a novel Multiple View Region Adaptive Multi-resolution in time Depth Motion Map (MV-RAMDMM) formulation combined with appearance information. Multiple stream 3D Convolutional Neural Networks (CNNs) are trained on the different views and time resolutions of the region adaptive Depth Motion Maps. Multiple views are synthesised to enhance the view invariance. The region adaptive weights, based on localised motion, accentuate and differentiate parts of actions possessing faster motion. Dedicated 3D CNN streams for multi-time resolution appearance information (RGB) are also included. These help to identify and differentiate between small object interactions. A pre-trained 3D-CNN is used here with fine-tuning for each stream along with multiple class Support Vector Machines (SVM)s. Average score fusion is used on the output. The developed approach is capable of recognising both human action and human-object interaction. Three public domain datasets including: MSR 3D Action,Northwestern UCLA multi-view actions and MSR 3D daily activity are used to evaluate the proposed solution. The experimental results demonstrate the robustness of this approach compared with state-of-the-art algorithms.

cs.CV↗

arXiv2010

First Smart Spaces

This document describes the Gloss software currently implemented. The description of the Gloss demonstrator for multi-surface interaction can be found in D17. The ongoing integration activity for the work described in D17 and D8 constitutes our development of infrastructure for a first smart space. In this report, the focus is on infrastructure to support the implementation of location aware services. A local architecture provides a framework for constructing Gloss applications, termed assemblies, that run on individual physical nodes. A global architecture defines an overlay network for linking individual assemblies. Both local and global architectures are under active development.

cs.DC↗

arXiv2010

Architectural Support for Global Smart Spaces

A GLObal Smart Space (GLOSS) provides support for interaction amongst people, artefacts and places while taking account of both context and movement on a global scale. Crucial to the definition of a GLOSS is the provision of a set of location-aware services that detect, convey, store and exploit location information. We use one of these services, hearsay, to illustrate the implementation dimensions of a GLOSS. The focus of the paper is on both local and global software architecture to support the implementation of such services. The local architecture is based on XML pipe-lines and is used to construct location-aware components. The global architecture is based on a hybrid peer-to-peer routing scheme and provides the local architectures with the means to communicate in the global context.

cs.DC↗