Author name cluster

Xiao Chen

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.

29 papers

2 author rows

EAAI Journal 2026 Journal Article

Irrelevance discriminative network for enhancing cross-center generalization in medical imaging segmentation

Yibin Lin
Dongming Li
Xiao Chen
Wude He
Qi Guan
Danru Chen
Anguo Zhang
Xiaorong Yan

Cross-center generalization in medical image segmentation (MIS) is a significant challenge due to the variability introduced by different imaging devices, operator techniques, and patient populations. In this paper, we propose the deep learning based Irrelevance Discriminative Network (ID-Net) method, which enhances cross-center generalization in MIS. We incorporate multiple auxiliary domain datasets (ADDs) from various centers alongside a single or limited number of target domain datasets. By training on the ADDs, the Irrelevance Discriminative (ID) module is capable of discriminating the latent representation of input images into common features, domain-specific features, and disturbance/noise. This allows for the fusion of common features with domain-specific features from the target domain dataset while discarding irrelevant noise, thereby significantly improving the cross-center generalization ability in the target domain tasks. Our approach effectively mitigates the domain shift problem and enhances the robustness and adaptability of MIS models across different centers.

Details DOI

AAAI Conference 2026 Conference Paper

MoETTA: Test-Time Adaptation Under Mixed Distribution Shifts with MoE-LayerNorm

Xiao Fan
Jingyan Jiang
Zhaoru Chen
Fanding Huang
Xiao Chen
Qinting Jiang
Bowen Zhang
Xing Tang

Test-time adaptation (TTA) has proven effective in mitigating performance drops under single-domain distribution shifts by updating model parameters during inference. However, real-world deployments often involve mixed distribution shifts---where test samples are affected by diverse and potentially conflicting domain factors---posing significant challenges even for state-of-the-art TTA methods. A key limitation in existing approaches is their reliance on a unified adaptation path, which fails to account for the fact that optimal gradient directions can vary significantly across different domains. Moreover, current benchmarks focus only on synthetic or homogeneous shifts, failing to capture the complexity of real-world heterogeneous mixed distribution shifts. To address this, we propose MoETTA, a novel entropy-based TTA framework that integrates the Mixture-of-Experts (MoE) architecture. Rather than enforcing a single parameter update rule for all test samples, MoETTA introduces a set of structurally decoupled experts, enabling specialization along diverse gradient directions. This design allows the model to better accommodate heterogeneous shifts through flexible and disentangled parameter updates. To simulate realistic deployment conditions, we introduce two new benchmarks: potpourri and potpourri+. While classical settings focus solely on synthetic corruptions (i.e., ImageNet-C), potpourri encompasses a broader range of domain shifts—including natural, artistic, and adversarial distortions—capturing more realistic deployment challenges. On top of that, potpourri+ further includes source-domain samples to evaluate robustness against catastrophic forgetting. Extensive experiments across three mixed distribution shifts settings show that MoETTA consistently outperforms strong baselines, establishing new state-of-the-art performance and highlighting the benefit of modeling multiple adaptation directions via expert-level diversity.

PDF Details DOI

AAAI Conference 2025 Conference Paper

FIRM: Flexible Interactive Reflection ReMoval

Xiao Chen
Xudong Jiang
Yunkang Tao
Zhen Lei
Qing Li
Chenyang Lei
Zhaoxiang Zhang

Removing reflection from a single image is challenging due to the absence of general reflection priors. Although existing methods incorporate extensive user guidance for satisfactory performance, they often lack the flexibility to adapt user guidance in different modalities, and dense user interactions further limit their practicality. To alleviate these problems, this paper presents FIRM, a novel framework for Flexible Interactive image Reflection reMoval with various forms of guidance, where users can provide sparse visual guidance (e.g., points, boxes, or strokes) or text descriptions for better reflection removal. Firstly, we design a novel user guidance conversion module (UGC) to transform different forms of guidance into unified contrastive masks. The contrastive masks provide explicit cues for identifying reflection and transmission layers in blended images. Secondly, we devise a contrastive mask-guided reflection removal network that comprises a newly proposed contrastive guidance interaction block (CGIB). This block leverages a unique cross-attention mechanism that merges contrastive masks with image features, allowing for precise layer separation. The proposed framework requires only 10% of the guidance time needed by previous interactive methods, which makes a step-change in flexibility. Extensive results on public real-world reflection removal datasets validate that our method demonstrates state-of-the-art reflection removal performance.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Label-Efficient Data Augmentation with Video Diffusion Models for Guidewire Segmentation in Cardiac Fluoroscopy

Shaoyan Pan
Yikang Liu
Lin Zhao
Eric Z. Chen
Xiao Chen
Terrence Chen
Shanhui Sun

The accurate segmentation of guidewires in interventional cardiac fluoroscopy videos is crucial for computer-aided navigation tasks. Although deep learning methods have demonstrated high accuracy and robustness in wire segmentation, they require substantial annotated datasets for generalizability, underscoring the need for extensive labeled data to enhance model performance. To address this challenge, we propose the Segmentation-guided Frame-consistency Video Diffusion Model (SF-VD) to generate large collections of labeled fluoroscopy videos, augmenting the training data for wire segmentation networks. SF-VD leverages videos with limited annotations by independently modeling scene distribution and motion distribution. It first samples the scene distribution by generating 2D fluoroscopy images with wires positioned according to a specified input mask, and then samples the motion distribution by progressively generating subsequent frames, ensuring frame-to-frame coherence through a frame-consistency strategy. A segmentation-guided mechanism further refines the process by adjusting wire contrast, ensuring a diverse range of visibility in the synthesized image. Evaluation on a fluoroscopy dataset confirms the superior quality of the generated videos and shows significant improvements in guidewire segmentation.

PDF Details DOI

IROS Conference 2025 Conference Paper

Model-Mediated Teleoperation with 3D Dynamic Environment Tracking (MMT-DET): A Comparative Study of Task Performance with Time-Domain Passivity Control

Diego Fernandez Prado
Xiao Chen
Jean Elsner
Hamid Sadeghian
Nader Rajaei
Abdeldjallil Naceri
Sami Haddadin
Eckehard G. Steinbach

Teleoperation with haptic feedback allows users to interact with remote environments while retaining a sense of touch. However, the stability and transparency of these systems are compromised under communication network delay. This paper presents an augmented Model-Mediated Teleoperation with 3D object and dynamic environment tracking (MMT-DET) by a vision-based algorithm, enabling users to receive haptic feedback in structured dynamic environments while maintaining robustness against network delays. A user study comparing the proposed method with teleoperation using the Time Domain Passivity Approach (TDPA) was conducted. The results demonstrate that our MMT-DET exhibits robustness to varying delays in task performance and outperforms TDPA at higher delay levels.

Details

IJCAI Conference 2025 Conference Paper

Where Does This Data Come From? Enhanced Source Inference Attacks in Federated Learning

Haiyang Chen
Xiaolong Xu
Xiang Zhu
Xiaokang Zhou
Fei Dai
Yansong Gao
Xiao Chen
Shuo Wang

Federated learning (FL) enables collaborative model training without exposing raw data, offering a privacy-aware alternative to centralized learning. However, FL remains vulnerable to various privacy attacks that exploit shared model updates, including membership inference, property inference, and gradient inversion. Source inference attacks further threaten FL by identifying which client contributed a specific training sample, posing severe risks to user and institutional privacy. Existing source inference attacks mainly assume passive adversaries and overlook more realistic scenarios where the server actively manipulates the training process. In this paper, we present an enhanced source inference attack that demonstrates how a malicious server can amplify behavioral differences between clients to more accurately infer data origin. Our approach introduces active training manipulation and data augmentation to expose client-specific patterns. Experimental results across five representative FL algorithms and multiple datasets show that our method significantly outperforms prior passive attacks. These findings reveal a deeper level of privacy vulnerability in FL and call for stronger defense mechanisms under active threat models.

PDF Details DOI

EAAI Journal 2024 Journal Article

AI-based optical-thermal video data fusion for near real-time blade segmentation in normal wind turbine operation

Xiaodong Jia
Xiao Chen

Blade damage inspection without stopping the normal operation of wind turbines has significant economic value. Blade segmentation is a fundamental task for blade damage inspection in the field without stopping wind turbines. This study proposes an AI-based method AQUADA-Seg to segment the images of blades from complex backgrounds by fusing optical and thermal videos taken from normal operating wind turbines. The method follows an encoder–decoder architecture and uses both optical and thermal videos to overcome the challenges associated with field application. A memory is designed between the encoder and decoder to improve the method’s performance by utilizing time history information in the videos to achieve temporal complementarity. The designed memory shares information between optical and thermal modalities to achieve multimodal complementarity. We collected a large-scale dataset, i. e. , 100 video pairs and over 55, 000 images, of optical-thermal videos of blades in operational wind turbines to train and test the method. Experimental results show that AQUADA-Seg: i) achieves near real-time thermal-optical blade video segmentation and can analyze videos with complex backgrounds in real-world field applications; ii) achieves 0. 996 and 0. 981 MIoU on optical and thermal videos, respectively, outperforming state-of-the-art methods, particularly in the videos with complex backgrounds. This study provides an essential step towards automated blade damage detection using computer vision without stopping the normal operation of wind turbines.

Details DOI

EAAI Journal 2024 Journal Article

Artificial intelligence-based blade identification in operational wind turbines through similarity analysis aided drone inspection

Shohreh Sheiati
Xiaodong Jia
Malcolm McGugan
Kim Branner
Xiao Chen

Tracking changes in wind turbine blade surface features over time, particularly during operation, is imperative for the early detection of potential damages. Advances in drone technology and Artificial Intelligence (AI) enable capturing and analysing numerous high-resolution blade images. It is essential to identify individual blades from inspection images captured at different times, despite potential changes in their surface features. Traditional AI-based classification algorithms could not link images of the same blades without retraining the system, hindering the identification process. In this study, we converted a classification problem into a similarity learning problem using Siamese Convolution Neural Networks (S-CNN) to automatically identify and retrieve corresponding blade images based on their unique visual surface features in response to a single query blade image, thereby eliminating the need to retrain the entire network. An advanced deep learning segmentation method is employed to segment the blade images as a preprocessing step to eliminate the influence of the image background on the identification task. The performance of the proposed model is verified using drone images of wind turbine blades, demonstrating near human-level precision in identifying images depicting the same individual blades.

Details DOI

ECAI Conference 2024 Conference Paper

Cliff: Leveraging Ambiguous Samples for Enhanced Test-Time Adaptation

Xiao Chen
Qihui Zhang
Yan Wang

Given the common scenario where a trained model confronts significant variations in data distributions different from the training data at test time, Test Time Adaptation (TTA) has emerged as a crucial field of study. Traditional methods in TTA have focused on filtering low-entropy samples to improve model performance, primarily through entropy minimization techniques. However, these approaches exhibit limitations as they often overlook the potential classes of high-entropy samples. This oversight can result in an inadequate utilization of available data, particularly under challenging conditions where model adaptability is critical. In contrast to conventional approaches, our work diverges from the sole emphasis on low-entropy samples by leveraging the rich information contained within ambiguous samples. We demonstrate that reliance solely on entropy minimization is detrimental when dealing with ambiguous samples. To address this, we introduce Cliff, a novel framework designed to learn from ambiguous samples effectively. Concretely, Cliff comprises two innovative components: Dynamic Recognition (DR) and Gap Raising Loss (GRL). DR proposes a method for identifying ambiguous samples and dynamically assigning weights to them, enhancing the model’s focus on potentially informative discrepancies. Whereas the proposed GRL, indeed theoretically proven to be beneficial to the model, guides the model in effectively distinguishing among potential classes by emphasizing the differences in their predictive probabilities. Extensive experiments conducted on CIFAR-10-C and CIFAR-100-C datasets demonstrate Cliff’s state-of-the-art performance. Our results show an average accuracy improvement of 20. 24% and 21. 12% over the direct use of source domain models on target domains, respectively.

Details

NeurIPS Conference 2024 Conference Paper

DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Rendering

Zhongpai Gao
Benjamin Planche
Meng Zheng
Xiao Chen
Terrence Chen
Ziyan Wu

Digitally reconstructed radiographs (DRRs) are simulated 2D X-ray images generated from 3D CT volumes, widely used in preoperative settings but limited in intraoperative applications due to computational bottlenecks. Physics-based Monte Carlo simulations provide accurate representations but are extremely computationally intensity. Analytical DRR renderers are much more efficient, but at the price of ignoring anisotropic X-ray image formation phenomena such as Compton scattering. We propose a novel approach that balances realistic physics-inspired X-ray simulation with efficient, differentiable DRR generation using 3D Gaussian splatting (3DGS). Our direction-disentangled 3DGS (DDGS) method decomposes the radiosity contribution into isotropic and direction-dependent components, able to approximate complex anisotropic interactions without complex runtime simulations. Additionally, we adapt the 3DGS initialization to account for tomography data properties, enhancing accuracy and efficiency. Our method outperforms state-of-the-art techniques in image accuracy and inference speed, demonstrating its potential for intraoperative applications and inverse problems like pose registration.

PDF Details DOI

ICRA Conference 2024 Conference Paper

Enhancing the Tracking Performance of Passivity-based High-Frequency Robot Cloud Control

Fabian Jakob
Xiao Chen
Hamid Sadeghian
Sami Haddadin

This paper addresses the migration of high-frequency robot controllers to remote computing services, which are connected via a communication channel prone to delays and packet loss. The stability of the networked system is guaranteed by ensuring passivity of each subcomponent in the interconnection, as well as the Time-Domain-Passivity-Approach (TDPA) for the communication channel. We reduce conservatism of the TDPA using the model knowledge on both sides of the communication system to identify passivity excesses. This is further used to avoid over-dissipation of energy in the passivity controller by augmentation of a tolerable passivity-shortage. Tracking offsets are eliminated with a position drift compensation algorithm, for which convergence guarantees are provided. The experimental validation of the results conducted on a 7-DoF Franka Research 3 robot demonstrates a substantial enhancement in tracking performance due to the proposed modifications, particularly in scenarios with high communication delays.

Details

ICRA Conference 2024 Conference Paper

Environment-Modulated Self-Assembly by Changes in Modules' Buoyancy

Xiao Chen
Junyi Han
Xin Jin
Shuhei Miyashita

While many inkjet printers employ only four types of ink (i. e. CKMY) to produce a wide range of colors, numerous technical challenges still exist for contemporary 3D printers to fabricate various materials and generate composite products such as electric devices. Conversely, there have been attempts and endeavors to make things through self-assembly of parts, analogous to the autonomous and decentralized development process of the human body from just 20 types of amino acids. In our previous work, we proposed a method for the rapid production of 3D objects using the centimeter-sized modules (referred to as Roblets) capable of generating a 2D structure and subsequently self-folding themselves into a 3D configuration, akin to origami. To further leverage the capability of generating a wide variety of different types of structures by combining different modules, this research studies a method of automatically selecting and supplying modules using environmental cues. More precisely, we developed a mechanism to couple different modules corresponding to three different environments (on a flat surface, on low-dense saline, and on saturated saline) and yielded different module configurations. The process of self-assembly necessitated the application of perturbation, which was realized by imparting magnetic torque originating from an external magnetic field onto the magnets embedded in the modules.

Details

ICRA Conference 2023 Conference Paper

A Force-Sensitive Exoskeleton for Teleoperation: An Application in Elderly Care Robotics

Alexander Toedtheide
Xiao Chen
Hamid Sadeghian
Abdeldjallil Naceri
Sami Haddadin

With the increasing demand for new healthcare solutions and technologies, such as those resulting from the COVID-19 crisis, and the growing elderly population, exoskeletons for teleoperation are a promising solution for many future medical applications. In this context, we propose two force- sensitive upper-limb exoskeletons for teleoperation, that are characterized by: i) torque-controlled robotic actuators, ii) rigid-body model compensations, and iii) a lightweight design achieved through the use of Bowden cable transmissions and remotely placed actuators. Specifically, we present a semi-active upper-limb exoskeleton for which we demonstrate human- device interaction control and bilateral teleoperation with force- feedback, evaluated via simulation, in the lab and over the Internet. We also introduce a design for a future fully-active upper-limb exoskeleton with two contact force/torque sensors, for a dual-arm device, which features a novel 3-degrees-of- freedom exoskeleton shoulder design and a contact wrench mitigation controller, as demonstrated through simulation. With this work, we propose the essential technical steps towards a novel teleoperation system for elderly care.

Details

ICRA Conference 2023 Conference Paper

A Passivity-based Approach on Relocating High-Frequency Robot Controller to the Edge Cloud

Xiao Chen
Hamid Sadeghian
Lingyun Chen
Mario Tröbinger
Abadalla Swirkir
Abdeldjallil Naceri
Sami Haddadin

As robots become more and more intelligent, the complexity of the algorithms behind them is increasing. Since these algorithms require high computation power from the onboard robot controller, the weight of the robot and energy consumption increases. A promising solution to tackle this issue is to relocate the expensive computation to the cloud. In this pioneering work, the possibility of relocating a state-of-the-art nonlinear control is investigated. To this end, the Unified Force-Impedance Controller (UFIC) is relocated to a remote location and high frequency feedback loop is established by including the remote controller in the loop. Passivity analysis is used to ensure the stability of the whole system, comprising the robot in interaction with the environment, the communication channel, as well as the remote controller. The instability associated with the communication channel is resolved by Time Domain Passivity Approach (TDPA). The performance of the proposed framework is experimentally evaluated on a robot arm in interaction with the environment. The results illustrate the stability of the system to a time-varying delay of up to 50 ± 10ms.

Details

YNIMG Journal 2023 Journal Article

Comprehensive evaluation of harmonization on functional brain imaging for multisite data-fusion

Yu-Wei Wang
Xiao Chen
Chao-Gan Yan

To embrace big-data neuroimaging, harmonizing the site effect in resting-state functional magnetic resonance imaging (R-fMRI) data fusion is a fundamental challenge. A comprehensive evaluation of potentially effective harmonization strategies, particularly with specifically collected data, has been scarce, especially for R-fMRI metrics. Here, we comprehensively assess harmonization strategies from multiple perspectives, including tests on residual site effect, individual identification, test-retest reliability, and replicability of group-level statistical results, on widely used R-fMRI metrics across various datasets, including data obtained from participants with repetitive measures at different scanners. For individual identifiability (i.e., whether the same subject could be identified across R-fMRI data scanned across different sites), we found that, while most methods decreased site effects, the Subsampling Maximum-mean-distance based distribution shift correction Algorithm (SMA) and parametric unadjusted CovBat outperformed linear regression models, linear mixed models, ComBat series and invariant conditional variational auto-encoder in clustering accuracy. Test-retest reliability was better for SMA and parametric adjusted CovBat than unadjusted ComBat series and parametric unadjusted CovBat in the number of overlapped voxels. At the same time, SMA was superior to the latter in replicability in terms of the Dice coefficient and the scale of brain areas showing sex differences reproducibly observed across datasets. Furthermore, SMA better detected reproducible sex differences of ALFF under the site-sex confounded situation. Moreover, we designed experiments to identify the best target site features to optimize SMA identifiability, test-retest reliability, and stability. We noted both sample size and distribution of the target site matter and introduced a heuristic formula for selecting the target site. In addition to providing practical guidelines, this work can inform continuing improvements and innovations in harmonizing methodologies for big R-fMRI data.

Details DOI

ICRA Conference 2023 Conference Paper

Identification of a Generalized Base Inertial Parameter Set of Robotic Manipulators Considering Mounting Configurations

Mario Tröbinger
Abdeldjallil Naceri
Xiao Chen
Hamid Sadeghian
Sami Haddadin

Identifying the inertial parameters of real robotic manipulators is a fundamental step towards realistic modeling and better controller performances, which is crucial for safe human-robot interaction. Our work introduces a novel framework for identifying a generalized set of base inertial parameters of a serial link manipulator. This framework is designed to be adaptable to accommodate any new mounting configuration of the robot. Our theoretical analysis highlights the influence of the robot's mounting configuration on the emergence of new parameters that cannot be identified through the conventional vertical base-axis mounting approach studied previously. To validate our proposed framework, we carried out two main experiments: the first involved simulation to establish the feasibility of our concept, and in the second, our framework was employed on a Franka Emika Robot in a real-world scenario to demonstrate and validate our approach. Our simulation results confirmed the feasibility of our proposed framework, while our real-world experiment successfully identified the generalized base inertial parameter set and validated its applicability to a new robot mounting configuration.

Details

YNIMG Journal 2023 Journal Article

Neural representations of self-generated thought during think-aloud fMRI

Hui-Xian Li
Bin Lu
Yu-Wei Wang
Xue-Ying Li
Xiao Chen
Chao-Gan Yan

Is the brain at rest during the so-called resting state? Ongoing experiences in the resting state vary in unobserved and uncontrolled ways across time, individuals, and populations. However, the role of self-generated thoughts in resting-state fMRI remains largely unexplored. In this study, we collected real-time self-generated thoughts during "resting-state" fMRI scans via the think-aloud method (i.e., think-aloud fMRI), which required participants to report whatever they were currently thinking. We first investigated brain activation patterns during a think-aloud condition and found that significantly activated brain areas included all brain regions required for speech. We then calculated the relationship between divergence in thought content and brain activation during think-aloud and found that divergence in thought content was associated with many brain regions. Finally, we explored the neural representation of self-generated thoughts by performing representational similarity analysis (RSA) at three neural scales: a voxel-wise whole-brain searchlight level, a region-level whole-brain analysis using the Schaefer 400-parcels, and at the systems level using the Yeo seven-networks. We found that "resting-state" self-generated thoughts were distributed across a wide range of brain regions involving all seven Yeo networks. This study highlights the value of considering ongoing experiences during resting-state fMRI and providing preliminary methodological support for think-aloud fMRI.

Details DOI

IJCAI Conference 2023 Conference Paper

VideoMaster: A Multimodal Micro Game Video Recreator

Yipeng Yu
Xiao Chen
Hui Zhan

To free human from laborious video production, this paper proposes the building of VideoMaster, a multimodal system equipped with four capabilities: highlight extraction, video describing, video dubbing and video editing. It extracts interesting episodes from long game videos, generates subtitles for each episode, reads the subtitles through synthesized speech, and finally re-creates a better short video through video editing. Notably, VideoMaster takes a combination of deep learning and traditional computer vision techniques to extract highlights with fine-to-coarse labels, utilizes a novel framework named PCSG-v (probabilistic context sensitive grammar for video) for video description generation, and imitates a target speaker's voice to read the description. To the best of our knowledge, VideoMaster is the first multimedia system that can automatically produce product-level micro-videos without heavy human annotation.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

M4Singer: A Multi-Style, Multi-Singer and Musical Score Provided Mandarin Singing Corpus

Lichao Zhang
Ruiqi Li
Shoutong Wang
Liqun Deng
Jinglin Liu
Yi Ren
JinZheng He
Rongjie Huang

The lack of publicly available high-quality and accurately labeled datasets has long been a major bottleneck for singing voice synthesis (SVS). To tackle this problem, we present M4Singer, a free-to-use Multi-style, Multi-singer Mandarin singing collection with elaborately annotated Musical scores as well as its benchmarks. Specifically, 1) we construct and release a large high-quality Chinese singing voice corpus, which is recorded by 20 professional singers, covering 700 Chinese pop songs as well as all the four SATB types (i. e. , soprano, alto, tenor, and bass); 2) we take extensive efforts to manually compose the musical scores for each recorded song, which are necessary to the study of the prosody modeling for SVS. 3) To facilitate the use and demonstrate the quality of M4Singer, we conduct four different benchmark experiments: score-based SVS, controllable singing voice (CSV), singing voice conversion (SVC) and automatic music transcription (AMT).

PDF Details

IROS Conference 2022 Conference Paper

On the Communication Channel in Bilateral Teleoperation: An Experimental Study for Ethernet, WiFi, LTE and 5G

Xiao Chen
Lars Johannsmeier
Hamid Sadeghian
Erfan Shahriari
Martin Danneberg
Anselm Nicklas
Fan Wu 0015
Gerhard P. Fettweis

Teleoperated robots are believed to play an important role for future applications in industry, medicine and other domains. Examples for this are remote assembly and maintenance, surgery, diagnosis or deep-sea and space exploration. Such applications are made possible by state-of-the-art tactile manipulators, well-researched control schemes and novel communication technologies such as the fifth generation of mobile communication (5G). The achievable performance is highly dependent on the communication delay and thus on the distance between leader and follower station, as well as the potentially used wireless protocol. Specially in this regard, 5G is a promising technology compared to the other communication protocols for transferring tactile information. In this paper, we introduce our telepresence reference platform, which can be used for empirical evaluation of different algorithms and communications. Comparative analysis are conducted to capture the influence of wireless communication protocols on telepresence systems consisting of complex robotic arms. The experiment compares the influence of 5G, LTE and WiFi communication protocols with regard to the motion and force tracking performance of the system.

Details

IROS Conference 2022 Conference Paper

Origami Robot Self-folding by Magnetic Induction

Jialun Liu
Xiao Chen
Quentin Lahondes
Kaan Esendag
Dana D. Damian
Shuhei Miyashita

Inspired by the traditional art of paper folding, origami, autonomous production of 3D structures from 2D sheets can be achieved by the implementation of self-folding techniques. One technique to achieve such transformation is the usage of thermo-responsive smart materials such as self-folding polymeric films, which can be controlled by heat to shrink. Achieving remote self-folding with a practical approach remains a major challenge due to the requirement for specific environments, or having to accompany electronics on origami, which limits the complexity of the origami design. In this paper, we present a wireless method to trigger the thermo-responsive self-folding process of the origami robots through magnetic induction. The proposed method is applicable for all electrically conductive materials and can wirelessly fold a mobile origami robot with a size of 32 × 30 mm 2. This method eliminates the need for inclusion of electronics on the origami or usage of complicated trigger methods and environmental conditions, allowing the robot to fold in a wider range of applications such as in constrained spaces.

Details

IJCAI Conference 2021 Conference Paper

A Streaming End-to-End Framework For Spoken Language Understanding

Nihal Potdar
Anderson Raymundo Avila
Chao Xing
Dong Wang
Yiran Cao
Xiao Chen

End-to-end spoken language understanding (SLU) recently attracted increasing interest. Compared to the conventional tandem-based approach that combines speech recognition and language understanding as separate modules, the new approach extracts users' intentions directly from the speech signals, resulting in joint optimization and low latency. Such an approach, however, is typically designed to process one intent at a time, which leads users to have to take multiple rounds to fulfill their requirements while interacting with a dialogue system. In this paper, we propose a streaming end-to-end framework that can process multiple intentions in an online and incremental way. The backbone of our framework is a unidirectional RNN trained with the connectionist temporal classification (CTC) criterion. By this design, an intention can be identified when sufficient evidence has been accumulated, and multiple intentions will be identified sequentially. We evaluate our solution on the Fluent Speech Commands (FSC) dataset and the detection accuracy is about 97 % on all multi-intent settings. This result is comparable to the performance of the state-of-the-art non-streaming models, but is achieved in an online and incremental way. We also employ our model to an keyword spotting task using the Google Speech Commands dataset, and the results are also highly promising.

PDF Details DOI

YNICL Journal 2020 Journal Article

Altered resting-state dynamic functional brain networks in major depressive disorder: Findings from the REST-meta-MDD consortium

Yicheng Long
Hengyi Cao
Chaogan Yan
Xiao Chen
Le Li
Francisco Xavier Castellanos
Tongjian Bai
Qijing Bo

BACKGROUND: Major depressive disorder (MDD) is known to be characterized by altered brain functional connectivity (FC) patterns. However, whether and how the features of dynamic FC would change in patients with MDD are unclear. In this study, we aimed to characterize dynamic FC in MDD using a large multi-site sample and a novel dynamic network-based approach. METHODS: Resting-state functional magnetic resonance imaging (fMRI) data were acquired from a total of 460 MDD patients and 473 healthy controls, as a part of the REST-meta-MDD consortium. Resting-state dynamic functional brain networks were constructed for each subject by a sliding-window approach. Multiple spatio-temporal features of dynamic brain networks, including temporal variability, temporal clustering and temporal efficiency, were then compared between patients and healthy subjects at both global and local levels. RESULTS: ). Corresponding local changes in MDD were mainly found in the default-mode, sensorimotor and subcortical areas. Measures of temporal variability and characteristic temporal path length were significantly correlated with depression severity in patients (corrected p < 0.05). Moreover, the observed between-group differences were robustly present in both first-episode, drug-naïve (FEDN) and non-FEDN patients. CONCLUSIONS: Our findings suggest that excessive temporal variations of brain FC, reflecting abnormal communications between large-scale bran networks over time, may underlie the neuropathology of MDD.

Details DOI

AAAI Conference 2020 Conference Paper

Dialog State Tracking with Reinforced Data Augmentation

Yichun Yin
Lifeng Shang
Xin Jiang
Xiao Chen
Qun Liu

Neural dialog state trackers are generally limited due to the lack of quantity and diversity of annotated training data. In this paper, we address this difﬁculty by proposing a reinforcement learning (RL) based framework for data augmentation that can generate high-quality data to improve the neural state tracker. Speciﬁcally, we introduce a novel contextual bandit generator to learn ﬁne-grained augmentation policies that can generate new effective instances by choosing suitable replacements for speciﬁc context. Moreover, by alternately learning between the generator and the state tracker, we can keep reﬁning the generative policies to generate more highquality training data for neural state tracker. Experimental results on the WoZ and MultiWoZ (restaurant) datasets demonstrate that the proposed framework signiﬁcantly improves the performance over the state-of-the-art models, especially with limited training data.

PDF Details

NeurIPS Conference 2020 Conference Paper

DynaBERT: Dynamic BERT with Adaptive Width and Depth

Lu Hou
Zhiqi Huang
Lifeng Shang
Xin Jiang
Xiao Chen
Qun Liu

The pre-trained language models like BERT, though powerful in many natural language processing tasks, are both computation and memory expensive. To alleviate this problem, one approach is to compress them for specific tasks before deployment. However, recent works on BERT compression usually compress the large BERT model to a fixed smaller size, and can not fully satisfy the requirements of different edge devices with various hardware performances. In this paper, we propose a novel dynamic BERT model (abbreviated as DynaBERT), which can flexibly adjust the size and latency by selecting adaptive width and depth. The training process of DynaBERT includes first training a width-adaptive BERT and then allowing both adaptive width and depth, by distilling knowledge from the full-sized model to small sub-networks. Network rewiring is also used to keep the more important attention heads and neurons shared by more sub-networks. Comprehensive experiments under various efficiency constraints demonstrate that our proposed dynamic BERT (or RoBERTa) at its largest size has comparable performance as BERT-base (or RoBERTa-base), while at smaller widths and depths consistently outperforms existing BERT compression methods. Code is available at https: //github. com/huawei-noah/Pretrained-Language-Model/tree/master/DynaBERT.

PDF Details

YNIMG Journal 2020 Journal Article

Rumination and the default mode network: Meta-analysis of brain imaging studies and implications for depression

Hui-Xia Zhou
Xiao Chen
Yang-Qian Shen
Le Li
Ning-Xuan Chen
Zhi-Chen Zhu
Francisco Xavier Castellanos
Chao-Gan Yan

Rumination is strongly and consistently correlated with depression. Although multiple studies have explored the neural correlates of rumination, findings have been inconsistent and the mechanisms underlying rumination remain elusive. Functional brain imaging studies have identified areas in the default mode network (DMN) that appear to be critically involved in ruminative processes. However, a meta-analysis to synthesize the findings of brain regions underlying rumination is currently lacking. Here, we conducted a meta-analysis consisting of experimental tasks that investigate rumination by using Signed Differential Mapping of 14 fMRI studies comprising 286 healthy participants. Furthermore, rather than treat the DMN as a unitary network, we examined the contribution of three DMN subsystems to rumination. Results confirm the suspected association between rumination and DMN activation, specifically implicating the DMN core regions and the dorsal medial prefrontal cortex subsystem. Based on these findings, we suggest a hypothesis of how DMN regions support rumination and present the implications of this model for treating major depressive disorder characterized by rumination.

Details DOI

YNIMG Journal 2020 Journal Article

The subsystem mechanism of default mode network underlying rumination: A reproducible neuroimaging study

Xiao Chen
Ning-Xuan Chen
Yang-Qian Shen
Hui-Xian Li
Le Li
Bin Lu
Zhi-Chen Zhu
Zhen Fan

Rumination is a repetitive self-referential thinking style that is often interpreted as an expression of abnormalities of the default mode network (DMN) observed during “resting-state” in major depressive disorder (MDD). Recent evidence has demonstrated that the DMN is not unitary but can be further divided into 3 functionally heterogenous subsystems, although the subsystem mechanistically underlying rumination remains unclear. Due to the unconstrained and indirect correlational nature of previous resting-state fMRI studies on rumination's network underpinnings, a paradigm allowing direct investigation of network interactions during active rumination is needed. Here, with a modified continuous state-like paradigm, we induced healthy participants to ruminate or imagine objective scenarios (distraction, as a control condition) on 3 different MRI scanners. We compared functional connectivities (FC) of the DMN and its 3 subsystems between rumination and distraction states. Results yielded a highly reproducible and dissociated pattern. During rumination, within-DMN FC was generally decreased as compared to the distraction state. At the subsystem level, we found increased FC between the core and medial temporal lobe (MTL) subsystem as well as decreased FC between the core and dorsal medial prefrontal cortex (DMPFC) subsystem and within the MTL subsystem. Finally, subjects’ behavioral measures of rumination and brooding were negatively correlated with FC between the core and DMPFC subsystems. These results suggest active rumination involves enhanced constraint by the core subsystem on the MTL subsystem and decreased coupling between the core and DMPFC subsystem, allowing for more information exchange among those involved DMN components. Furthermore, the reproducibility of our findings provides a rigorous evaluation of their validity and significance.

Details DOI

YNICL Journal 2019 Journal Article

Physiological significance of R-fMRI indices: Can functional metrics differentiate structural lesions (brain tumors)?

Zhen Fan
Xiao Chen
Zeng-Xin Qi
Le Li
Bin Lu
Cong-Lin Jiang
Ren-Qing Zhu
Chao-Gan Yan

Resting-state functional MRI (R-fMRI) research has recently entered the era of "big data", however, few studies have provided a rigorous validation of the physiological underpinnings of R-fMRI indices. Although studies have reported that various neuropsychiatric disorders exhibit abnormalities in R-fMRI measures, these "biomarkers" have not been validated in differentiating structural lesions (brain tumors) as a concept proof. We enrolled 60 patients with intracranial tumors located in the unilateral cranialcavity and 60 matched normal controls to test whether R-fMRI indices can differentiate tumors, which represents a prerequisite for adapting such indices as biomarkers for neuropsychiatric disorders. Common R-fMRI indices of tumors and their counterpart control regions, which were defined as the contralateral normal areas (for amplitude of low frequency fluctuations (ALFF), fractional ALFF (fALFF), regional homogeneity (ReHo) and degree centrality (DC)) and ipsilateral regions surrounding the tumors (for voxel-mirrored homotopic connectivity (VMHC)), were comprehensively assessed. According to robust paired t-tests with a Bonferroni correction, only VMHC (Fisher's r-to-z transformed) could successfully differentiate substantial tumors from their counterpart normal regions in patients. Furthermore, ALFF and DC were not able to differentiate tumor from normal unless Z-standardization was employed. To validate the lower power of the between-subject design compared to the within-subject design, each metric was calculated in a matched control group, and robust two-sample t-tests were used to compare the patient tumors and the normal controls at the same place. Similarly, only VMHC succeeded in differentiating significant differences between tumors and the sham tumor areas of normal controls. This study tested the premise of R-fMRI biomarkers for differentiating lesions, and brings a new understanding to physical significance of the Z-standardization.

Details DOI

IJCAI Conference 2013 Conference Paper

Combine Constituent and Dependency Parsing via Reranking

Xiaona Ren
Xiao Chen
Chunyu Kit

This paper presents a reranking approach to combining constituent and dependency parsing, aimed at improving parsing performance on both sides. Most previous combination methods rely on complicated joint decoding to integrate graph- and transition-based dependency models. Instead, our approach makes use of a high-performance probabilistic context free grammar (PCFG) model to output k-best candidate constituent trees, and then a dependency parsing model to rerank the trees by their scores from both models, so as to get the most probable parse. Experimental results show that this reranking approach achieves the highest accuracy of constituent and dependency parsing on Chinese treebank (CTB5. 1) and a comparable performance to the state of the art on English treebank (WSJ).

PDF Details DOI