Author name cluster

Xiaoyan Wu

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.

11 papers

2 author rows

EAAI Journal 2026 Journal Article

An adaptive dual-graph spatial–temporal convolutional network with edge-aware fusion for elderly gait recognition using Kinect-based skeleton data

Botao Wang
Xiaoyan Wu
Jianning Wu
Qingxin Zeng
Zhaoming Lin

The accurate recognition of elderly gait patterns can significantly contribute to clinical applications such as elderly health monitoring and fall risk prediction. However, how to develop a high-generalization elderly gait classification model has become a challenging problem in elderly gait quantization analysis. Considering the interaction coupling changes across joints in the kinetic chains of elderly gait, we propose an advanced adaptive edge-aware dual-graph convolutional network (AEDGCN) for high-accuracy elderly gait recognition. Our model integrates a gait-graph and a gait-hypergraph to capture high-order joint interaction coupling, which reflects subtle differences in elderly gait changes. By modeling these fine-grained spatial–temporal dependencies, the proposed model achieves strong generalization in accurately identifying elderly gait patterns. Specifically, the proposed technique employs an Edge-Aware Mechanism (EAM) to simultaneously model local spatial dependencies between joints from the gait-graph and cross-joint correlations from the gait-hypergraph. Additionally, the Hierarchical Deep Fully Convolution (HDFC) module is designed to enhance the modeling of temporal dependencies across multiple scales. Our Kinect-based gait dataset, comprising 45 healthy younger participants and 34 healthy elderly participants, with three walking patterns, is used to evaluate the feasibility of our method. In addition, experiments on the public KINECAL dataset further demonstrate the generalization capability of the proposed model. The experimental results confirm that our model outperforms state-of-the-art methods while keeping a low learning complexity. The proposed method effectively enables modeling of elderly gait dynamics, providing informative feature representations for understanding age-related locomotion changes and supporting downstream clinical assessments

Details DOI

AAAI Conference 2026 Conference Paper

READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head Generation

Haotian Wang
Yuzhe Weng
Jun Du
Haoran Xu
Xiaoyan Wu
Shan He
Bing Yin
Cong Liu

The introduction of diffusion models has brought significant advances to the field of audio-driven talking head generation. However, the extremely slow inference speed severely limits the practical implementation of diffusion-based talking head generation models. In this study, we propose READ, a real-time diffusion-transformer-based talking head generation framework. Our approach first learns a spatiotemporal highly compressed video latent space via a temporal VAE, significantly reducing the token count to accelerate generation. To achieve better audio-visual alignment within this compressed latent space, a pre-trained Speech Autoencoder (SpeechAE) is proposed to generate temporally compressed speech latent codes corresponding to the video latent space. These latent representations are then modeled by a carefully designed Audio-to-Video Diffusion Transformer (A2V-DiT) backbone for efficient talking head synthesis. Furthermore, to ensure temporal consistency and accelerated inference in extended generation, we propose a novel asynchronous noise scheduler (ANS) for both the training and inference processes of our framework. The ANS leverages asynchronous add-noise and asynchronous motion-guided generation in the latent space, ensuring consistency in generated video clips. Experimental results demonstrate that READ outperforms state-of-the-art methods by generating competitive talking head videos with significantly reduced runtime, achieving an optimal balance between quality and speed while maintaining robust metric stability in long-time generation.

PDF Details DOI

YNIMG Journal 2026 Journal Article

The roles of human hippocampus and orbitofrontal cortex in cognitive map-guided social transitive inference

Yuanyuan Yang
Jinhui Li
Yidan Qiu
Xiaoqian Jiang
Xiaoyan Wu
Ruiwang Huang

Cognitive maps support flexible inference by organizing relational structures across experiences. This enables humans and animals to integrate knowledge and infer indirect relationships, a process known as transitive inference (TI). While the hippocampus (HPC) and orbitofrontal cortex (OFC) are both important for cognitive mapping, their specific roles in TI remain unclear. Here, we obtained behavioral and fMRI data from 25 healthy adults to study how they learned face rankings along two social dimensions (competence and popularity) and how they inferred novel relationships between untrained face pairs. Compared with control condition, we found that during TI, the bilateral HPC, left middle frontal gyrus (MFG), insula, and superior temporal gyrus (STG) showed significantly greater activation and stronger functional connectivity (FC) within the TI network. The HPC can significantly distinguish the dimension-related from dimension-unrelated hub faces. In addition, we found that the HPC had stronger FC with the regions of the default mode network, dorsal attention network, and mid-cingulate cortex when processing dimension-related hubs compared to dimension-unrelated hubs. These findings revealed the key role of the HPC in encoding abstract relational structure and how it collaborates with large-scale brain networks to support cognitive map-guided transitive inference.

Details DOI

EAAI Journal 2025 Journal Article

A novel adaptive spatial–temporal cross-graph convolutional fusion learning network for skeleton-based abnormal gait recognition

Liang Wang
Xiaoyan Wu
Bin Wu
Jianning Wu

Developing graph-based abnormal gait classification models with high generalization has been a challenging problem in gait analysis. In this study, a novel adaptive spatial–temporal cross-graph convolutional fusion learning network is proposed to accurately recognize skeleton-based abnormal gait patterns. In the proposed model, with an adaptive fusion adjacency matrix including self-adaptive adjacency matrices and cross-adaptive adjacency matrices, a joint–bone gait graph convolutional fusion learning algorithm is constructed to capture spatial gait abnormality features hidden in skeleton data. A temporal convolution network is then adopted to explore temporal dependencies of gait abnormality embedded in the spatial feature space. This could discover the most discriminative spatial–temporal gait abnormality representations containing richer information about interaction coupling across joints and bones for high-generalization. The skeleton data of mimic abnormal gait from 57 participants were collected to evaluate the feasibility of our model. The experimental results based on the leave-one-subject-out (LOSO) cross-validation scheme show that our proposed model reaches the optimal performance with the highest accuracy of 99. 43%, and significantly outcompetes several recent state-of-the-art models. Our model can feasibly take advantage of the adaptive fusion adjacency matrix to greatly enhance the aggregation degree of joints and bones. This helps to learn excellent gait abnormality representations containing richer interaction information for high generalization while keeping a low learning complexity. Our findings hopefully provide a powerful technical solution for abnormal gait recognition in practical clinical application.

Details DOI

YNIMG Journal 2024 Journal Article

Processing demands modulate the activities and functional connectivity patterns of the posterior (VWFA-1) and anterior (VWFA-2) VWFA

Aqian Li
Chuansheng Chen
Xiaoyan Wu
Yuan Feng
Jingyu Yang
Xiaoxue Feng
Rui Hu
Leilei Mei

Previous studies have shown that the visual word form area (VWFA) has structural and intrinsic functional connectivity with both language and attention networks. Nevertheless, it is still unclear how the functional connectivity pattern of the VWFA is regulated by processing demands induced by experimental tasks, and whether processing demands differentially regulate the posterior (VWFA-1) and anterior (VWFA-2) subregions of the VWFA. To address these questions, the present study adopted two tasks varying in processing demands (i.e., verbal and non-verbal tasks), and used generalized psychophysiological interaction (gPPI) and dynamic causal modeling (DCM) analyses to explore the task-dependent functional connectivity patterns of the two subregions of the VWFA. Activation analysis revealed that the VWFA-2 showed higher activation for the verbal task than the non-verbal task, while there were no activation differences in the VWFA-1 after controlling for the stimulus driven effects. Functional and effective connectivity analyses revealed that, for both VWFA-1 and VWFA-2, the verbal task enhanced connections from VWFAs to the ventral language regions (e.g., the left orbital frontal cortex), while the non-verbal task enhanced connections from VWFAs to the dorsal visuospatial regions (e.g., the left intraparietal sulcus). Results of the present study indicate that processing demands induced by tasks modulate both the local activity and functional connectivity patterns of the VWFA, providing new insights for understanding its domain-general function.

Details DOI

YNIMG Journal 2024 Journal Article

Unraveling the influences of hemodynamic lag and intrinsic cerebrovascular reactivity on functional metrics in ischemic stroke

Luoyu Wang
Xiumei Wu
Jinyi Song
Yanhui Fu
Zhenqiang Ma
Xiaoyan Wu
Yiying Wang
Yulin Song

Resting-state functional magnetic resonance imaging (rs-fMRI) is a prominent tool for investigating functional deficits in stroke patients. However, the extent to which the hemodynamic lags (LAG) and the intrinsic cerebrovascular reactivity (iCVR) may affect the rs-fMRI metrics in different scales needs to be clarified for ischemic stroke. In this study, 73 ischemic stroke patients and 74 healthy controls (HC) were recruited to investigate how the correction of the LAG and/or iCVR would influence resting-state functional magnetic resonance imaging (rs-fMRI) metrics of three different spatial scales (local-scale, meso-scale and global-scale) in ischemic stroke. The analysis revealed that the Stroke pattern of all functional metrics using different correction strategies resembled the HC pattern. The highest overlap was observed in the Stroke pattern with correction for both LAG and iCVR, while the pattern without correction showed the lowest overlap. Most functional metrics after correction showed higher sensitivity in detecting between-group differences than those without correction. Moreover, our results were generally reproducible in an independent dataset. Collectively, these findings emphasize the necessity of considering LAG and iCVR effects to investigate stroke-related functional alterations, and highlight the significance of correction strategies for accurately interpreting the findings in rs-fMRI study of ischemic stroke.

Details DOI

EAAI Journal 2024 Journal Article

WAL-Net: Weakly supervised auxiliary task learning network for carotid plaques classification

Haitao Gan
Lingchao Fu
Ran Zhou
Weiyan Gan
Furong Wang
Xiaoyan Wu
Zhi Yang
Zhongwei Huang

The classification of carotid artery ultrasound images is a crucial step for diagnosing carotid plaques, holding significant clinical relevance for predicting the risk of stroke. Recent research suggests that utilizing supervised plaque segmentation as an auxiliary task for classification can enhance performance by leveraging the correlation between segmentation and classification tasks. However, this approach relies on obtaining a substantial amount of challenging-to-acquire segmentation annotations. This paper proposes a novel weakly supervised auxiliary task learning network model (WAL-Net) to explore the interdependence between carotid plaque classification and segmentation tasks. The plaque classification task is the primary one, while the plaque segmentation task serves as the auxiliary one, providing valuable information to enhance the performance of the primary task. Weakly supervised learning is adopted in the auxiliary task in which the segmentation masks are not provided. Experiments and evaluations are conducted on a dataset comprising 1270 carotid plaque ultrasound images from Wuhan University Zhongnan Hospital. Results indicate that WAL-Net achieved an approximately 1. 3% improvement in carotid plaque classification accuracy compared to the baseline network. Specifically, the accuracy of mixed-echoic plaques classification increased by approximately 3. 3%, demonstrating the effectiveness of WAL-Net.

Details DOI

YNICL Journal 2023 Journal Article

Frequency-dependent and time-variant alterations of neural activity in post-stroke depression: A resting-state fMRI study

Xiumei Wu
Luoyu Wang
Haibo Jiang
Yanhui Fu
Tiantian Wang
Zhenqiang Ma
Xiaoyan Wu
Yiying Wang

BACKGROUND: Post-stroke depression (PSD) is one of the most frequent psychiatric disorders after stroke. However, the underlying brain mechanism of PSD remains unclarified. Using the amplitude of low-frequency fluctuation (ALFF) approach, we aimed to investigate the abnormalities of neural activity in PSD patients, and further explored the frequency and time properties of ALFF changes in PSD. METHODS: Resting-state fMRI data and clinical data were collected from 39 PSD patients (PSD), 82 S patients without depression (Stroke), and 74 age- and sex-matched healthy controls (HC). ALFF across three frequency bands (ALFF-Classic: 0.01-0.08 Hz; ALFF-Slow4: 0.027-0.073 Hz; ALFF-Slow5: 0.01-0.027 Hz) and dynamic ALFF (dALFF) were computed and compared among three groups. Ridge regression analyses and spearman's correlation analyses were further applied to explore the relationship between PSD-specific alterations and depression severity in PSD. RESULTS: We found that PSD-specific alterations of ALFF were frequency-dependent and time-variant. Specially, compared to both Stroke and HC groups, PSD exhibited increased ALFF in the contralesional dorsolateral prefrontal cortex (DLPFC) and insula in all three frequency bands. Increased ALFF in ipsilesional DLPFC were observed in both slow-4 and classic frequency bands which were positively correlated with depression scales in PSD, while increased ALFF in the bilateral hippocampus and contralesional rolandic operculum were only found in slow-5 frequency band. These PSD-specific alterations in different frequency bands could predict depression severity. Moreover, decreased dALFF in contralesional superior temporal gyrus were observed in PSD group. LIMITATIONS: Longitudinal studies are required to explore the alterations of ALFF in PSD as the disease progress. CONCLUSIONS: The frequency-dependent and time-variant properties of ALFF could reflect the PSD-specific alterations in complementary ways, which may assist to elucidate underlying neural mechanisms and be helpful for early diagnosis and interventions for the disease.

Details DOI

YNICL Journal 2023 Journal Article

Multi-modal MRI measures reveal sensory abnormalities in major depressive disorder patients: A surface-based study

Shufei Zhang
Shenglin She
Yidan Qiu
Zezhi Li
Xiaoyan Wu
Huiqing Hu
Wei Zheng
Ruiwang Huang

BACKGROUND: Multi-modal magnetic resonance imaging (MRI) measures are supposed to be able to capture different brain neurobiological aspects of major depressive disorder (MDD). A fusion analysis of structural and functional modalities may better reveal the disease biomarker specific to the MDD disease. METHODS: We recruited 30 MDD patients and 30 matched healthy controls (HC). For each subject, we acquired high-resolution brain structural images and resting-state fMRI (rs-fMRI) data using a 3 T MRI scanner. We first extracted the brain morphometric measures, including the cortical volume (CV), cortical thickness (CT), and surface area (SA), for each subject from the structural images, and then detected the structural clusters showing significant between-group differences in each measure using the surface-based morphology (SBM) analysis. By taking the identified structural clusters as seeds, we performed seed-based functional connectivity (FC) analyses to determine the regions with abnormal FC in the patients. Based on a logistic regression model, we performed a classification analysis by selecting these structural and functional cluster-wise measures as features to distinguish the MDD patients from the HC. RESULTS: The MDD patients showed significantly lower CV in a cluster involving the right superior temporal gyrus (STG) and middle temporal gyrus (MTG), and lower SA in three clusters involving the bilateral STG, temporal pole gyrus, and entorhinal cortex, and the left inferior temporal gyrus, and fusiform gyrus, than the controls. No significant difference in CT was detected between the two groups. By taking the above-detected clusters as seeds to perform the seed-based FC analysis, we found that the MDD patients showed significantly lower FC between STG/MTG (CV's cluster) and two clusters located in the bilateral visual cortices than the controls. The logistic regression model based on the structural and functional features reached a classification accuracy of 86.7% (p < 0.001) between MDD and controls. CONCLUSION: The present study showed sensory abnormalities in MDD patients using the multi-modal MRI analysis. This finding may act as a disease biomarker distinguishing MDD patients from healthy individuals.

Details DOI

YNIMG Journal 2021 Journal Article

From gratitude to injustice: Neurocomputational mechanisms of gratitude-induced injustice

Ruida Zhu
Zhenhua Xu
Song Su
Chunliang Feng
Yi Luo
Honghong Tang
Shen Zhang
Xiaoyan Wu

Gratitude shapes individuals' behaviours and impacts the harmony of society. Many previous studies focused on its association with prosocial behaviours. A possibility that gratitude can lead to moral violation has been overlooked until recently. Nevertheless, the neurocognitive mechanisms of gratitude-induced moral violation are still unclear. On the other hand, though neural correlates of the gratitude's formation have been examined, the neural underpinnings of gratitude-induced behaviour remain unknown. For addressing these two overlapped research gaps, we developed novel tasks to investigate how participants who had received voluntary (Gratitude group) or involuntary help (Control group) punished their benefactors' unfairness with functional magnetic resonance imaging (fMRI). The Gratitude group punished their benefactors less than the Control group. The self-report and computational modelling results demonstrated a crucial role of the boosted protection tendency on behalf of benefactors in the gratitude-induced injustice. The fMRI results showed that activities in the regions associated with mentalizing (temporoparietal junction) and reward processing (ventral medial prefrontal cortex) differed between the groups and were related to the gratitude-induced injustice. They suggest that grateful individuals concern for benefactors' benefits, value chances to interact with benefactors, and refrain from action that perturbs relationship-building (i.e., exert less punishment on benefactors' unfairness), which reveal a dark side of gratitude and enrich the gratitude theory (i.e., the find-bind-remind theory). Our findings provide psychological, computational, and neural accounts of the gratitude-induced behaviour and further the understanding of the nature of gratitude.

Details DOI

ICRA Conference 1996 Conference Paper

Force and motion transmissibility in dextrous manipulation

Xiaoyan Wu
Inmin Kao

In this paper, we discuss the transmissibility of force and motion in the analysis of dextrous manipulation with sliding using soft fingers. The transmissibility of force is a well-known principle in mechanics, which states that the force can be transmitted along its line of action. The motion transmissibility, however, is not ubiquitous. The investigation of such mechanics principles in dextrous manipulation yields interesting results which have very important implications on the analysis of dextrous manipulation regarding the motion and force at the contacts. A coefficient, C/sub e/, is found to relate the magnitude of velocity after the point of contact is transmitted to another locations. We compare such transmissibilities using rigid-body and nonrigid-body motion analysis. Examples are presented to illustrate their usage in dextrous manipulation.

Details