Author name cluster

Yunlong Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

2 author rows

AAAI Conference 2026 Conference Paper

Artificial Immune System of Secure Face Recognition Against Adversarial Attacks (Abstract Reprint)

Min Ren
Yunlong Wang
Yuhao Zhu
Yongzhen Huang
Zhenan Sun
Qi Li
Tieniu Tan

Deep learning-based face recognition models are vulnerable to adversarial attacks. In contrast to general noises, the presence of imperceptible adversarial noises can lead to catastrophic errors in deep face recognition models. The primary difference between adversarial noise and general noise lies in its specificity. Adversarial attack methods give rise to noises tailored to the characteristics of the individual image and recognition model at hand. Diverse samples and recognition models can engender specific adversarial noise patterns, which pose significant challenges for adversarial defense. Addressing this challenge in the realm of face recognition presents a more formidable endeavor due to the inherent nature of face recognition as an open set task. In order to tackle this challenge, it is imperative to employ customized processing for each individual input sample. Drawing inspiration from the biological immune system, which can identify and respond to various threats, this paper aims to create an artificial immune system to provide adversarial defense for face recognition. The proposed defense model incorporates the principles of antibody cloning, mutation, selection, and memory mechanisms to generate a distinct antibody for each input sample, wherein the term antibody refers to a specialized noise removal manner. Furthermore, we introduce a self-supervised adversarial training mechanism that serves as a simulated rehearsal of immune system invasions. Extensive experimental results demonstrate the efficacy of the proposed method, surpassing state-of-the-art adversarial defense methods.

PDF Details DOI

EAAI Journal 2026 Journal Article

Interval adaptive multi-objective optimization of the proton exchange membrane fuel cell system considering parameter perturbation

Yunlong Wang
Yongfu Wang

The performance of the proton exchange membrane (PEM) fuel cell system varies with setpoints of operation variables, especially under the parameter perturbation. To enhance the multiple performance indexes under uncertain conditions, this paper introduces an artificial intelligence driven optimization algorithm, i. e. , the interval adaptive multi-objective optimization scheme for the PEM fuel cell system. Initially, a steady-state nonlinear fuel cell system model is established in detail and the influence between uncertain parameters and system performance is analyzed. A nonparametric kernel density estimation method is used to obtain the uncertainty distribution function and probability interval. Additionally, considering the conflicts of multi-performance indexes including the output power and system efficiency, an interval adaptive multi-objective particle swarm optimization (IAMOPSO) method is introduced for the selection of operation variables. To improve the quality of Pareto solutions, an adaptive strategy with particle uniformity index is designed for the flight parameter adjustment. Finally, based on the result of the probability interval of the objective function, the interval non-dominated optimal set is obtained. Different optimization algorithms are implemented in the simulation and hardware-in-loop (HIL) experiments. Compared with the non-dominated sorting genetic algorithm-II (NSGA-II) method, the multi-objective particle swarm optimization (MOPSO) method and the varying weight multi-objective particle swarm optimization (vwMOPSO) method, the proposed IAMOPSO method performs better in the indexes including the mean system efficiency 0. 2028, the mean net power 31840 Watt (W) for a 381-cell stack, and hypervolume (HV) metric 0. 2930.

Details DOI

NeurIPS Conference 2025 Conference Paper

Embodied Crowd Counting

Runling Long
Yunlong Wang
Jia Wan
Xiang Deng
Xinting Zhu
Weili Guan
Antoni Chan
Liqiang Nie

Occlusion is one of the fundamental challenges in crowd counting. In the community, various data-driven approaches have been developed to address this issue, yet their effectiveness is limited. This is mainly because most existing crowd counting datasets on which the methods are trained are based on passive cameras, restricting their ability to fully sense the environment. Recently, embodied navigation methods have shown significant potential in precise object detection in interactive scenes. These methods incorporate active camera settings, holding promise in addressing the fundamental issues in crowd counting. However, most existing methods are designed for indoor navigation, showing unknown performance in analyzing complex object distribution in large-scale scenes, such as crowds. Besides, most existing embodied navigation datasets are indoor scenes with limited scale and object quantity, preventing them from being introduced into dense crowd analysis. Based on this, a novel task, Embodied Crowd Counting (ECC), is proposed to count the number of persons in a large-scale scene actively. We then build up an interactive simulator, the Embodied Crowd Counting Dataset (ECCD), which enables large-scale scenes and large object quantities. A prior probability distribution approximating a realistic crowd distribution is introduced to generate crowds. Then, a zero-shot navigation method (ZECC) is proposed as a baseline. This method contains an MLLM-driven coarse-to-fine navigation mechanism, enabling active Z-axis exploration, and a normal-line-based crowd distribution analysis method for fine counting. Experimental results show that the proposed method achieves the best trade-off between counting accuracy and navigation cost. Code can be found at https: //github. com/longrunling/ECC? .

PDF Details

JBHI Journal 2025 Journal Article

TTFNet: Temporal-Frequency Features Fusion Network for Speech Based Automatic Depression Recognition and Assessment

Xiyuan Chen
Zhuhong Shao
Yinan Jiang
Runsen Chen
Yunlong Wang
Bicao Li
Mingyue Niu
Hongguang Chen

Related studies have revealed that the phonological features of depressed patients are different from those of healthy individuals. With the increasing prevalence of depression, an objective and convenient approach for early screening is necessary. To this end, we propose an automatic depression detection method based on hybrid speech features extracted by deep learning, dubbed as TTFNet. Firstly, to effectively excavate the intrinsic relationship among multidimensional dynamic features in the frequency domain, the log-Mel spectrogram of raw speech and its related derivatives are encoded into quaternion representation. Then, the innovatively designed quaternion VisionLSTM is utilized to capture their synergistic effects. Simultaneously, we integrate sLSTM with the pre-trained wav2vec 2. 0 model to fully acquire the temporal features. In addition, to further exploit the complementarity between temporal and frequency features, we design an XConformer block for cross-sequence interactions, which ingeniously combines self-attention mechanisms and convolutional modules. Based on this block, the dual-path fusion module closely utilizes the mutual promotion of features from different domains, thereby enhancing generalization capability of the proposed model. Extensive experiments conducted on the AVEC 2013, AVEC 2014, DAIC-WOZ and E-DAIC datasets demonstrate that our method outperforms current state-of-the-art methods in both depression recognition and severity prediction tasks.

Details DOI

IROS Conference 2024 Conference Paper

6-DoF Grasp Detection in Clutter with Enhanced Receptive Field and Graspable Balance Sampling

Hanwen Wang
Ying Zhang
Yunlong Wang
Jian Li

6-DoF grasp detection of small-scale grasps is crucial for robots to perform specific tasks. This paper focuses on enhancing the recognition capability of small-scale grasping, aiming to improve the overall accuracy of grasping prediction results and the generalization ability of the network. We propose an enhanced receptive field method that includes a multi-radii cylinder grouping module and a passive attention module. This method enhances the receptive field area within the graspable space and strengthens the learning of graspable features. Additionally, we design a graspable balance sampling module based on a 3D segmentation network, which enables the network to focus on features of small objects, thereby improving the recognition capability of small-scale grasping. Our network achieves state-of-the-art performance on the GraspNet-1Billion dataset, with an overall improvement of approximately 10% in average precision@k (AP). Furthermore, we deployed our grasp detection model on pybullet grasping platform and in real-world scenarios, which validates the effectiveness of our method.

Details

NeurIPS Conference 2024 Conference Paper

Boosting the Transferability of Adversarial Attack on Vision Transformer with Adaptive Token Tuning

Di Ming
Peng Ren
Yunlong Wang
Xin Feng

Vision transformers (ViTs) perform exceptionally well in various computer vision tasks but remain vulnerable to adversarial attacks. Recent studies have shown that the transferability of adversarial examples exists for CNNs, and the same holds true for ViTs. However, existing ViT attacks aggressively regularize the largest token gradients to exact zero within each layer of the surrogate model, overlooking the interactions between layers, which limits their transferability in attacking black-box models. Therefore, in this paper, we focus on boosting the transferability of adversarial attacks on ViTs through adaptive token tuning (ATT). Specifically, we propose three optimization strategies: an adaptive gradient re-scaling strategy to reduce the overall variance of token gradients, a self-paced patch out strategy to enhance the diversity of input tokens, and a hybrid token gradient truncation strategy to weaken the effectiveness of attention mechanism. We demonstrate that scaling correction of gradient changes using gradient variance across different layers can produce highly transferable adversarial examples. In addition, introducing attentional truncation can mitigate the overfitting over complex interactions between tokens in deep ViT layers to further improve the transferability. On the other hand, using feature importance as a guidance to discard a subset of perturbation patches in each iteration, along with combining self-paced learning and progressively more sampled attacks, significantly enhances the transferability over attacks that use all perturbation patches. Extensive experiments conducted on ViTs, undefended CNNs, and defended CNNs validate the superiority of our proposed ATT attack method. On average, our approach improves the attack performance by 10. 1% compared to state-of-the-art transfer-based attacks. Notably, we achieve the best attack performance with an average of 58. 3% on three defended CNNs. Code is available at https: //github. com/MisterRpeng/ATT.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Learning Explicit Contact for Implicit Reconstruction of Hand-Held Objects from Monocular Images

Junxing Hu
Hongwen Zhang
Zerui Chen
Mengcheng Li
Yunlong Wang
Yebin Liu
Zhenan Sun

Reconstructing hand-held objects from monocular RGB images is an appealing yet challenging task. In this task, contacts between hands and objects provide important cues for recovering the 3D geometry of the hand-held objects. Though recent works have employed implicit functions to achieve impressive progress, they ignore formulating contacts in their frameworks, which results in producing less realistic object meshes. In this work, we explore how to model contacts in an explicit way to benefit the implicit reconstruction of hand-held objects. Our method consists of two components: explicit contact prediction and implicit shape reconstruction. In the first part, we propose a new subtask of directly estimating 3D hand-object contacts from a single image. The part-level and vertex-level graph-based transformers are cascaded and jointly learned in a coarse-to-fine manner for more accurate contact probabilities. In the second part, we introduce a novel method to diffuse estimated contact states from the hand mesh surface to nearby 3D space and leverage diffused contact probabilities to construct the implicit neural representation for the manipulated object. Benefiting from estimating the interaction patterns between the hand and the object, our method can reconstruct more realistic object meshes, especially for object parts that are in contact with hands. Extensive experiments on challenging benchmarks show that the proposed method outperforms the current state of the arts by a great margin. Our code is publicly available at https://junxinghu.github.io/projects/hoi.html.

PDF Details DOI

IROS Conference 2024 Conference Paper

ToolEENet: Tool Affordance 6D Pose Estimation

Yunlong Wang
Lei Zhang 0198
Yuyang Tu
Hui Zhang 0070
Kaixin Bai
Zhaopeng Chen
Jianwei Zhang 0001

The exploration of robotic dexterous hands utilizing tools has recently attracted considerable attention. A significant challenge in this field is the precise awareness of a tool’s pose when grasped, as occlusion by the hand often degrades the quality of the estimation. Additionally, the tool’s overall pose often fails to accurately represent the contact interaction, thereby limiting the effectiveness of vision-guided, contact-dependent activities. To overcome this limitation, we present the innovative TOOLEE dataset, which, to the best of our knowledge, is the first to feature affordance segmentation of a tool’s end-effector (EE) along with its defined 6D pose based on its usage. Furthermore, we propose the ToolEENet framework for accurate 6D pose estimation of the tool’s EE. This framework begins by segmenting the tool’s EE from raw RGB-D data, then uses a diffusion model-based pose estimator for 6D pose estimation at a category-specific level. Addressing the issue of symmetry in pose estimation, we introduce a symmetry-aware pose representation that enhances the consistency of pose estimation. Our approach excels in this field, demonstrating high levels of precision and generalization. Furthermore, it shows great promise for application in contact-based manipulation scenarios. All data and codes are available on the project website: https://tooleenet-iros2024.github.io/

Details

EAAI Journal 2023 Journal Article

Pressure and oxygen excess ratio control of PEMFC air management system based on neural network and prescribed performance

Yunlong Wang
Yongfu Wang

The simultaneous control of the pressure and oxygen excess ratio (OER) plays an important role in improving the performance and safety of polymer electrolyte membrane fuel cell (PEMFC). Nevertheless, the coupling characteristics and nonlinearity existing in the PEMFC air management system need to be solved. To this end, the original coupled nonlinear PEMFC air management system is first transformed into the cathode pressure and OER subsystems by using input–output linearization. For the cathode pressure subsystem, the neural network (NN) control scheme is proposed to maintain the stable tracking of cathode pressure. For the OER subsystem, a prescribed performance function (PPF) is proposed and therefore, the overshoot and steady state of OER tracking error is guaranteed within the quantitative boundary. Moreover, the restriction that the initial error is within the performance function bound is relaxed by proposing a tuning function. Finally, the Lyapunov stability theory, numerical simulations and hardware-in-loop (HIL) experiments show the effectiveness of the proposed controller. Compared with the proportional integral derivative (PID) controller, NN controller without PPF and NN controller with conventional PPF, the NN controller with the proposed PPF can realize the quantitative adjustment of OER and give more improvements to the system safety.

Details DOI

ICML Conference 2023 Conference Paper

Towards Trustworthy Explanation: On Causal Rationalization

Wenbo Zhang 0010
Tong Wu
Yunlong Wang
Yong Cai
Hengrui Cai

With recent advances in natural language processing, rationalization becomes an essential self-explaining diagram to disentangle the black box by selecting a subset of input texts to account for the major variation in prediction. Yet, existing association-based approaches on rationalization cannot identify true rationales when two or more snippets are highly inter-correlated and thus provide a similar contribution to prediction accuracy, so-called spuriousness. To address this limitation, we novelly leverage two causal desiderata, non-spuriousness and efficiency, into rationalization from the causal inference perspective. We formally define a series of probabilities of causation based on a newly proposed structural causal model of rationalization, with its theoretical identification established as the main component of learning necessary and sufficient rationales. The superior performance of the proposed causal rationalization is demonstrated on real-world review and medical datasets with extensive experiments compared to state-of-the-art methods.

Details

AAAI Conference 2021 Conference Paper

eTREE: Learning Tree-structured Embeddings

Faisal M. Almutairi
Yunlong Wang
Dong Wang
Emily Zhao
Nicholas D. Sidiropoulos

Matrix factorization (MF) plays an important role in a wide range of machine learning and data mining models. MF is commonly used to obtain item embeddings and feature representations due to its ability to capture correlations and higherorder statistical dependencies across dimensions. In many applications, the categories of items exhibit a hierarchical tree structure. For instance, human diseases can be divided into coarse categories, e. g. , bacterial, and viral. These categories can be further divided into finer categories, e. g. , viral infections can be respiratory, gastrointestinal, and exanthematous viral diseases. In e-commerce, products, movies, books, etc. , are grouped into hierarchical categories, e. g. , clothing items are divided by gender, then by type (formal, casual, etc.). While the tree structure and the categories of the different items may be known in some applications, they have to be learned together with the embeddings in many others. In this work, we propose eTREE, a model that incorporates the (usually ignored) tree structure to enhance the quality of the embeddings. We leverage the special uniqueness properties of Nonnegative MF (NMF) to prove identifiability of eTREE. The proposed model not only exploits the tree structure prior, but also learns the hierarchical clustering in an unsupervised data-driven fashion. We derive an efficient algorithmic solution and a scalable implementation of eTREE that exploits parallel computing, computation caching, and warm start strategies. We showcase the effectiveness of eTREE on real data from various application domains: healthcare, recommender systems, and education. We also demonstrate the meaningfulness of the tree obtained from eTREE by means of domain experts interpretation.

PDF Details

JBHI Journal 2021 Journal Article

Exploiting Causality for Improved Prediction of Patient Volumes by Gaussian Processes

Guanchao Feng
Kezi Yu
Yunlong Wang
Yilian Yuan
Petar M. Djuric

Estimating and surveillance volumes of patients are of great importance for public health and resource allocation. In many situations, the change of these volumes is correlated with many factors, e. g. , seasonal environmental variables, medicine sales, and patient medical claims. It is often of interest to predict patient volumes and to that end, discovering causalities can improve the prediction accuracy. Correlations do not imply causations and they can be spurious, which in turn may entail deterioration of prediction performance if the prediction is based on them. By contrast, in this paper, we propose an approach for prediction based on causalities discovered by Gaussian processes. Our interest is in estimating volumes of patients that suffer from allergy and where the model and the results are highly interpretable. In selecting features, instead of only using correlation, we take causal information into account. Specifically, we adopt the Gaussian processes-based convergent cross mapping framework for causal discovery which is proven to be more reliable than the Granger causality when time series are coupled. Moreover, we introduce a novel method for selecting the history or look-back length of features from the perspective of a dynamical system in a principled manner. The quasi-periodicities that commonly exist in observations of volumes of patients and environment variables can readily be accommodated. Further, the proposed method performs well even in cases when the data are scarce. Also, the approach can be modified without much difficulty to forecast other types of patient volumes. We validate the method with synthetic and real-world datasets.

Details DOI

EAAI Journal 2021 Journal Article

Hybrid adaptive learning neural network control for steer-by-wire systems via sigmoid tracking differentiator and disturbance observer

Yunlong Wang
Yongfu Wang
Ming Tie

Steer-by-Wire (SbW) systems are usually affected negatively by the friction torque and self-aligning torque. This paper proposes a hybrid learning neural network controller to achieve precise control for the SbW system. Firstly, a sigmoid tracking differentiator (STD) is introduced to obtain the velocity signal with the angle measurement only. Secondly, by combining the model-free technology, the neural network is applied to overcome the lumped uncertainty including the friction torque and self-aligning torque. Different from the related literature, a second-order identification model is designed to construct the learning law so that the neural network can be adjusted by the tracking error and modeling error simultaneously. Finally, a disturbance observer is proposed for the compensation of compound disturbance including the external disturbance and neural network approximated error. The advantages are that the proposed control scheme not only ensures good tracking performance using the least sensors but also can handle uncertainty and attenuate measurement noise. Lyapunov stability theory proves that the tracking error is uniformly ultimately bounded. Numerical simulations and experiments show the effectiveness and superiorities of the proposed control method.

Details DOI

AAAI Conference 2020 Conference Paper

Dynamic Graph Representation for Occlusion Handling in Biometrics

Min Ren
Yunlong Wang
Zhenan Sun
Tieniu Tan

The generalization ability of Convolutional neural networks (CNNs) for biometrics drops greatly due to the adverse effects of various occlusions. To this end, we propose a novel uniﬁed framework integrated the merits of both CNNs and graphical models to learn dynamic graph representations for occlusion problems in biometrics, called Dynamic Graph Representation (DGR). Convolutional features onto certain regions are re-crafted by a graph generator to establish the connections among the spatial parts of biometrics and build Feature Graphs based on these node representations. Each node of Feature Graphs corresponds to a speciﬁc part of the input image and the edges express the spatial relationships between parts. By analyzing the similarities between the nodes, the framework is able to adaptively remove the nodes representing the occluded parts. During dynamic graph matching, we propose a novel strategy to measure the distances of both nodes and adjacent matrixes. In this way, the proposed method is more convincing than CNNs-based methods because the dynamic graph method implies a more illustrative and reasonable inference of the biometrics decision. Experiments conducted on iris and face demonstrate the superiority of the proposed framework, which boosts the accuracy of occluded biometrics recognition by a large margin comparing with baseline methods.

PDF Details