arXiv subjects

Yingjie Chen

Publications and source records attributed to Yingjie Chen.

At least 37 records · Page 2Linked to original sources

arXiv2023

Tunable morphing of electroactive dielectric-elastomer balloons

Designing smart devices with tunable shapes has important applications in industrial manufacture. In this paper, we investigate the nonlinear deformation and the morphological transitions between buckling, necking, and snap-through instabilities of layered DE balloons in response to an applied radial voltage and an inner pressure. We propose a general mathematical theory of nonlinear electro-elasticity able to account for finite inhomogeneous strains provoked by the electro-mechanical coupling. We investigate the onsets of morphological transitions of the spherically symmetric balloons using the surface impedance matrix method. Moreover, we study the nonlinear evolution of the bifurcated branches through finite element numerical simulations. Our analysis demonstrates the possibility to design tunable DE spheres, where the onset of buckling and necking can be controlled by geometrical and mechanical properties of the passive elastic layers. Relevant applications include soft robotics and mechanical actuators.

cond-mat.soft↗

arXiv2023

EventFormer: AU Event Transformer for Facial Action Unit Event Detection

Facial action units (AUs) play an indispensable role in human emotion analysis. We observe that although AU-based high-level emotion analysis is urgently needed by real-world applications, frame-level AU results provided by previous works cannot be directly used for such analysis. Moreover, as AUs are dynamic processes, the utilization of global temporal information is important but has been gravely ignored in the literature. To this end, we propose EventFormer for AU event detection, which is the first work directly detecting AU events from a video sequence by viewing AU event detection as a multiple class-specific sets prediction problem. Extensive experiments conducted on a commonly used AU benchmark dataset, BP4D, show the superiority of EventFormer under suitable metrics.

cs.CV↗

arXiv2022

Voltage-controlled topological interface states for bending waves in soft dielectric phononic crystal plates

The operating frequency range of passive topological phononic crystals is generally fixed and narrow, limiting their practical applications. To overcome this difficulty, here we design and investigate a one-dimensional soft dielectric phononic crystal (PC) plate system with actively tunable topological interface states via the mechanical and electric loads. We use nonlinear electroelasticity theory and linearized incremental theory to derive the governing equations. First we determine the nonlinear static response of the soft dielectric PC plate subjected to a combination of axial force and electric voltage. Then we study the motion of superimposed incremental bending waves. By adopting the Spectral Element Method, we obtain the dispersion relation for the infinite PC plate and the transmission coefficient for the finite PC plate waveguide. Numerical results show that the low-frequency topological interface state exists at the interface of the finite phononic plate waveguide with two topologically different elements. By simply adjusting the axial force or the electric voltage, an increase or decrease in the frequency of the topological interface state can be realized. Furthermore, applying the electric voltage separately on different elements of the PC plate waveguide is a flexible and smart method to tune the topological interface state in a wide range. These results provide guidance for designing soft smart wave devices with low-frequency tunable topological interface states.

cond-mat.soft↗

arXiv2022

Vibrations and waves in soft dielectric elastomer structures

Dielectric elastomers (DEs) are a type of multifunctional materials with salient features that are very attractive in developing soft, lightweight, and small-scale transducers and robotics. This paper reviews the mechanics of soft DE structures, focusing on their dynamic responses, including vibrations and waves in typical structures. The basic formulations of nonlinear electroelasticity are briefly summarized by following the descriptions of Dorfmann and Ogden. The recent advances in the study on linearized dynamic problems of DE plates and shells are then outlined according to the geometric configurations as well as the coordinates thereof adopted. Some interesting observations from the numerical results are highlighted, and the underlying physics is discussed. For completeness, an account of the nonlinear dynamic characteristics of DE structures is also given. For DE structures with a periodic arrangement, i.e., DE phononic crystals (PCs) or metamaterials, this paper reviews the designs, solutions, and results to illustrate the wide-range tunability of band structure that is realized by large reversible deformation and electromechanical coupling. The present literature survey could be a useful guide for future studies on the dynamic topics of DE structures.

cond-mat.soft↗

arXiv2022

Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian

Facial pose estimation refers to the task of predicting face orientation from a single RGB image. It is an important research topic with a wide range of applications in computer vision. Label distribution learning (LDL) based methods have been recently proposed for facial pose estimation, which achieve promising results. However, there are two major issues in existing LDL methods. First, the expectations of label distributions are biased, leading to a biased pose estimation. Second, fixed distribution parameters are applied for all learning samples, severely limiting the model capability. In this paper, we propose an Anisotropic Spherical Gaussian (ASG)-based LDL approach for facial pose estimation. In particular, our approach adopts the spherical Gaussian distribution on a unit sphere which constantly generates unbiased expectation. Meanwhile, we introduce a new loss function that allows the network to learn the distribution parameter for each learning sample flexibly. Extensive experimental results show that our method sets new state-of-the-art records on AFLW2000 and BIWI datasets.

cs.CV↗

arXiv2022

On Mitigating Hard Clusters for Face Clustering

Face clustering is a promising way to scale up face recognition systems using large-scale unlabeled face images. It remains challenging to identify small or sparse face image clusters that we call hard clusters, which is caused by the heterogeneity, \ie, high variations in size and sparsity, of the clusters. Consequently, the conventional way of using a uniform threshold (to identify clusters) often leads to a terrible misclassification for the samples that should belong to hard clusters. We tackle this problem by leveraging the neighborhood information of samples and inferring the cluster memberships (of samples) in a probabilistic way. We introduce two novel modules, Neighborhood-Diffusion-based Density (NDDe) and Transition-Probability-based Distance (TPDi), based on which we can simply apply the standard Density Peak Clustering algorithm with a uniform threshold. Our experiments on multiple benchmarks show that each module contributes to the final performance of our method, and by incorporating them into other advanced face clustering methods, these two modules can boost the performance of these methods to a new state-of-the-art. Code is available at: https://github.com/echoanran/On-Mitigating-Hard-Clusters.

cs.CV↗

arXiv2021

Blockchain Enabled Secure Authentication for Unmanned Aircraft Systems

The integration of air and ground smart vehicles is becoming a new paradigm of future transportation. A decent number of smart unmanned vehicles or UAS will be sharing the national airspace for various purposes, such as express delivery, surveillance, etc. However, the proliferation of UAS also brings challenges considering the safe integration of them into the current Air Traffic Management (ATM) systems. Especially when the current Automatic Dependent Surveillance Broadcasting (ADS-B) systems do not have message authentication mechanisms, it can not distinguish whether an authorized UAS is using the corresponding airspace. In this paper, we aim to address these practical challenges in two folds. We first use blockchain to provide a secure authentication platform for flight plan approval and sharing between the existing ATM facilities. We then use the fountain code to encode the authentication payloads and adapt them into the de facto communication protocol of ATM. This maintains backward compatibility and ensures the verification success rate under the noisy broadcasting channel. We simulate the realistic wireless communication scenarios and theoretically prove that our proposed authentication framework is with low latency and highly compatible with existing ATM communication protocols.

cs.CR↗

arXiv2021

DG-Labeler and DGL-MOTS Dataset: Boost the Autonomous Driving Perception

Multi-object tracking and segmentation (MOTS) is a critical task for autonomous driving applications. The existing MOTS studies face two critical challenges: 1) the published datasets inadequately capture the real-world complexity for network training to address various driving settings; 2) the working pipeline annotation tool is under-studied in the literature to improve the quality of MOTS learning examples. In this work, we introduce the DG-Labeler and DGL-MOTS dataset to facilitate the training data annotation for the MOTS task and accordingly improve network training accuracy and efficiency. DG-Labeler uses the novel Depth-Granularity Module to depict the instance spatial relations and produce fine-grained instance masks. Annotated by DG-Labeler, our DGL-MOTS dataset exceeds the prior effort (i.e., KITTI MOTS and BDD100K) in data diversity, annotation quality, and temporal representations. Results on extensive cross-dataset evaluations indicate significant performance improvements for several state-of-the-art methods trained on our DGL-MOTS dataset. We believe our DGL-MOTS Dataset and DG-Labeler hold the valuable potential to boost the visual perception of future transportation.

cs.CV↗

arXiv2021

Density-Based Clustering with Kernel Diffusion

Finding a suitable density function is essential for density-based clustering algorithms such as DBSCAN and DPC. A naive density corresponding to the indicator function of a unit $d$-dimensional Euclidean ball is commonly used in these algorithms. Such density suffers from capturing local features in complex datasets. To tackle this issue, we propose a new kernel diffusion density function, which is adaptive to data of varying local distributional characteristics and smoothness. Furthermore, we develop a surrogate that can be efficiently computed in linear time and space and prove that it is asymptotically equivalent to the kernel diffusion density function. Extensive empirical experiments on benchmark and large-scale face image datasets show that the proposed approach not only achieves a significant improvement over classic density-based clustering algorithms but also outperforms the state-of-the-art face clustering methods by a large margin.

cs.LG↗

arXiv2021

Zero-bias Deep Neural Network for Quickest RF Signal Surveillance

The Internet of Things (IoT) is reshaping modern society by allowing a decent number of RF devices to connect and share information through RF channels. However, such an open nature also brings obstacles to surveillance. For alleviation, a surveillance oracle, or a cognitive communication entity needs to identify and confirm the appearance of known or unknown signal sources in real-time. In this paper, we provide a deep learning framework for RF signal surveillance. Specifically, we jointly integrate the Deep Neural Networks (DNNs) and Quickest Detection (QD) to form a sequential signal surveillance scheme. We first analyze the latent space characteristic of neural network classification models, and then we leverage the response characteristics of DNN classifiers and propose a novel method to transform existing DNN classifiers into performance-assured binary abnormality detectors. In this way, we seamlessly integrate the DNNs with the parametric quickest detection. Finally, we propose an enhanced Elastic Weight Consolidation (EWC) algorithm with better numerical stability for DNNs in signal surveillance systems to evolve incrementally, we demonstrate that the zero-bias DNN is superior to regular DNN models considering incremental learning and decision fairness. We evaluated the proposed framework using real signal datasets and we believe this framework is helpful in developing a trustworthy IoT ecosystem.

cs.LG↗

arXiv2021

Effects of strain stiffening and electrostriction on tunable elastic waves in compressible dielectric elastomer laminates

This paper presents an electromechanical analysis of the nonlinear static response and the superimposed small-amplitude wave characteristics in an infinite periodic compressible dielectric elastomer (DE) laminate subjected to electrostatic excitations and prestress in the thickness direction. The enriched Gent material model is employed to account for the effects of strain stiffening and electrostriction of the DE laminate. The theory of nonlinear electroelasticity and related linearized incremental theory are exploited to derive the governing equations of nonlinear response and the dispersion relations of incremental shear and longitudinal waves. Numerical results reveal that the snap-through instability of a Gent DE laminate resulting from geometrical and material nonlinearities can be used to achieve a sharp transition in the position and width of wave band gaps. Furthermore, the influence of material properties (including Gent constants, the second strain invariant and electrostrictive parameters) and that of prestress on the snap-through instability and the electrostatic tunability of band gaps for both shear and longitudinal waves are discussed in detail. The electrostrictive effect and prestress are beneficial to stabilizing the periodic DE laminate. Depending on whether the snap-through instability occurs or not, a continuous variation or a sharp transition in wave band gaps can be realized by varying the electric stimuli. Our numerical findings are expected to provide a solid guidance for the design and manufacture of soft DE wave devices with tunable band structures.

cond-mat.soft↗

arXiv2021

Low-frequency tunable topological interface states in soft phononic crystal cylinders

Topological phononic crystals have attracted intensive attention due to their peculiar topologically protected interface or edge states. Their operating frequency, however, is generally fixed once designed and fabricated. Here, we propose to overcome this limitation by utilizing soft topological phononic crystals. In particular, we design a simple one-dimensional periodic system of soft cylindrical waveguides to realize mechanically tunable topological interface states for longitudinal waves. To this end, we employ the nonlinear elasticity theory and its linearized incremental version to fully account for both geometric and material nonlinearities of the system. We derive the dispersion relation for small-amplitude longitudinal motions superimposed on the finitely deformed state. In addition, our analytical results provide information about the corresponding Bloch wave modes, displacement field distributions, and signal transmission coefficients for finite cylindrical waveguides with identical or various unit-cell topologies. Our numerical results illustrate the low-frequency topological interface state occurring at the interface between two topologically distinct soft phononic cylinders. Moreover, we show that the corresponding frequency in the overlapped band gap can be continuously adjusted by an external force. This analytical result is also validated by the finite element simulations. Finally, we provide the topological phase diagrams to demonstrate the tunable position and existence condition of the topological interface states when tuning the external loading. The low-frequency tunable topological interface states with remarkable field enhancement may find a wide range of potential applications such as tunable energy harvesters, low-pass filters and high-sensitivity detectors for biomedical applications.

cond-mat.soft↗

arXiv2021

SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation

Video instance segmentation (VIS) is a new and critical task in computer vision. To date, top-performing VIS methods extend the two-stage Mask R-CNN by adding a tracking branch, leaving plenty of room for improvement. In contrast, we approach the VIS task from a new perspective and propose a one-stage spatial granularity network (SG-Net). Compared to the conventional two-stage methods, SG-Net demonstrates four advantages: 1) Our method has a one-stage compact architecture and each task head (detection, segmentation, and tracking) is crafted interdependently so they can effectively share features and enjoy the joint optimization; 2) Our mask prediction is dynamically performed on the sub-regions of each detected instance, leading to high-quality masks of fine granularity; 3) Each of our task predictions avoids using expensive proposal-based RoI features, resulting in much reduced runtime complexity per instance; 4) Our tracking head models objects centerness movements for tracking, which effectively enhances the tracking robustness to different object appearances. In evaluation, we present state-of-the-art comparisons on the YouTube-VIS dataset. Extensive experiments demonstrate that our compact one-stage method can achieve improved performance in both accuracy and inference speed. We hope our SG-Net could serve as a strong and flexible baseline for the VIS task. Our code will be available.

cs.CV↗

arXiv2021

DenserNet: Weakly Supervised Visual Localization Using Multi-scale Feature Aggregation

In this work, we introduce a Denser Feature Network (DenserNet) for visual localization. Our work provides three principal contributions. First, we develop a convolutional neural network (CNN) architecture which aggregates feature maps at different semantic levels for image representations. Using denser feature maps, our method can produce more keypoint features and increase image retrieval accuracy. Second, our model is trained end-to-end without pixel-level annotation other than positive and negative GPS-tagged image pairs. We use a weakly supervised triplet ranking loss to learn discriminative features and encourage keypoint feature repeatability for image representation. Finally, our method is computationally efficient as our architecture has shared features and parameters during computation. Our method can perform accurate large-scale localization under challenging conditions while remaining the computational constraint. Extensive experiment results indicate that our method sets a new state-of-the-art on four challenging large-scale localization benchmarks and three image retrieval benchmarks.

cs.CV↗

arXiv2021

Hierarchical Attention Fusion for Geo-Localization

Geo-localization is a critical task in computer vision. In this work, we cast the geo-localization as a 2D image retrieval task. Current state-of-the-art methods for 2D geo-localization are not robust to locate a scene with drastic scale variations because they only exploit features from one semantic level for image representations. To address this limitation, we introduce a hierarchical attention fusion network using multi-scale features for geo-localization. We extract the hierarchical feature maps from a convolutional neural network (CNN) and organically fuse the extracted features for image representations. Our training is self-supervised using adaptive weights to control the attention of feature emphasis from each hierarchical level. Evaluation results on the image retrieval and the large-scale geo-localization benchmarks indicate that our method outperforms the existing state-of-the-art methods. Code is available here: \url{https://github.com/YanLiqi/HAF}.

cs.CV↗

arXiv2020

A Vector-based Representation to Enhance Head Pose Estimation

This paper proposes to use the three vectors in a rotation matrix as the representation in head pose estimation and develops a new neural network based on the characteristic of such representation. We address two potential issues existed in current head pose estimation works: 1. Public datasets for head pose estimation use either Euler angles or quaternions to annotate data samples. However, both of these annotations have the issue of discontinuity and thus could result in some performance issues in neural network training. 2. Most research works report Mean Absolute Error (MAE) of Euler angles as the measurement of performance. We show that MAE may not reflect the actual behavior especially for the cases of profile views. To solve these two problems, we propose a new annotation method which uses three vectors to describe head poses and a new measurement Mean Absolute Error of Vectors (MAEV) to assess the performance. We also train a new neural network to predict the three vectors with the constraints of orthogonality. Our proposed method achieves state-of-the-art results on both AFLW2000 and BIWI datasets. Experiments show our vector-based annotation method can effectively reduce prediction errors for large pose angles.

cs.CV↗

arXiv2020

Visual Localization for Autonomous Driving: Mapping the Accurate Location in the City Maze

Accurate localization is a foundational capacity, required for autonomous vehicles to accomplish other tasks such as navigation or path planning. It is a common practice for vehicles to use GPS to acquire location information. However, the application of GPS can result in severe challenges when vehicles run within the inner city where different kinds of structures may shadow the GPS signal and lead to inaccurate location results. To address the localization challenges of urban settings, we propose a novel feature voting technique for visual localization. Different from the conventional front-view-based method, our approach employs views from three directions (front, left, and right) and thus significantly improves the robustness of location prediction. In our work, we craft the proposed feature voting method into three state-of-the-art visual localization networks and modify their architectures properly so that they can be applied for vehicular operation. Extensive field test results indicate that our approach can predict location robustly even in challenging inner-city settings. Our research sheds light on using the visual localization approach to help autonomous vehicles to find accurate location information in a city maze, within a desirable time constraint.

cs.CV↗

arXiv2019

Stabilizing effect of enhanced resistivity on peeling-ballooning instabilities on EAST

Previous stability analysis of NSTX equilibrium with lithium-conditioning demonstrates that the enhanced resistivity due to the increased effective charge number Zeff (i.e. increased impurity level) can provide a stabilizing effect on low-n edge localized modes (Banerjee et al 2017 Nucl. Fusion 24 054501). This paper extends the resistivity stabilizing effect to the intermediate-n peeling-ballooning (PB) instabilities with the linear stability analysis of EAST high-confinement mode equilibria in NIMROD two-fluid calculations. However, the resistivity stabilizing effect on PB instabilities in the EAST tokamak appears weaker than that found in NSTX. This work may give better insight into the physical mechanism behind the beneficial effects of impurity on the pedestal stability.

physics.plasm-ph↗