Author name cluster

Jun Lu

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.

13 papers

2 author rows

EAAI Journal 2026 Journal Article

A Point-Voxel Transformer for point cloud object detection with spatial and channel attention

Guangyu Ji
Jun Lu
Chengtao Cai
Kaibin Qin

Voxelization loss has a significant impact on small object detection. However, existing point-voxel based two-stage object detection methods mainly generate three-dimensional (3D) proposal boxes using voxel features. The coarse representation of point clouds by voxels can result in difficulty in accurately capturing fine-grained features of small objects, and the accuracy of 3D bounding box regression may also be compromised, impacting detection accuracy. To solve this problem, we propose a novel voxel-point based architecture, named Point-Voxel Spatial-Channel Transformer (PVCST), to represent objects using point features. PVCST consists of two modules: the Voxel-based Spatial-Channel Attention module (VCSA) and the Point-based Spatial-Channel Attention module (PCSA). The VCSA employs channel attention to enhance sensitivity to local feature variations within a voxel and spatial attention to capture relationships among object parts across voxels, enabling the network to construct more comprehensive object representations. PCSA uses channel attention to adjust the importance of features, enhancing adaptability to varying dataset conditions, and spatial attention to identify critical regions, suppress noise, and capture long-range dependencies in the point cloud. By integrating spatial features and channel features, which are two distinct types of geometric information, VCSA and PCSA enhance object feature representation, particularly for small objects. Since point clouds of small objects tend to be sparse, a richer representation is especially crucial for their accurate detection. PVCST generates 3D proposal boxes directly from point-based features and directly utilizes original point features in these proposals for classification and regression, ensuring the integrity of the original input data without introducing additional points during the parallel computation of the Transformer. PVCST achieves mean Average Precision (mAP) scores of 78. 31% and 70. 66% on LEVEL 1 and LEVEL 2 of the vehicle category on the Waymo 3D detection benchmark.

Details DOI

IS Journal 2026 Journal Article

A vehicle lateral stability criterion fusing phase plane and RBF neural network

Dequan Zeng
Lixiong Rao
Yiming Hu
Peizhi Zhang
Lu Xiong
Jun Lu
Giuseppe Carbone
Yinquan Yu

Precise stability criteria are essential for vehicle handling control, but conventional methods based on tire adhesion limits or linear models often lack robustness across diverse scenarios. To address this issue, this paper proposes a novel lateral stability criterion fusing phase plane analysis and RBF neural networks. The approach begins with an analysis of the vehicle’s stable state using the phase plane, followed by the division of the vehicle stability region employing the diamond method to generate a phase plane stability region database. Subsequently, the proposed phase plane-RBF stability criterion is constructed by leveraging the RBF neural network for nonlinear fitting of the stability region data, which is further refined through multiple rounds of optimization. Compared to traditional tire force and linear single-track model criteria, the proposed criterion demonstrates superior accuracy in identifying extreme conditions and enhanced adaptability across operational scenarios.

Details DOI

AAAI Conference 2026 Conference Paper

S2C: A Noise-Resistant Difference Learning Framework for Unsupervised Change Detection in VHR Remote Sensing Images

Lei Ding
Xibing Zuo
Haitao Guo
Jun Lu
Zhihui Gong
Xuanguang Liu
Jicang Lu

Unsupervised Change Detection (UCD) in Very High Resolution (VHR) Remote Sensing (RS) images remains to be a difficult challenge due to the inherent spatio-temporal complexity within data. Inspired by recent advancements in Visual Foundation Models (VFMs) and Contrastive Learning (CL), this research aims to develop CL methodologies to translate implicit knowledge in VFM into change representations, thus eliminating the need for explicit supervision. To this end, we introduce a Semantic-to-Change (S2C) learning framework for UCD in VHR RS images. Differently from existing CL methodologies that typically focus on learning multi-temporal similarities, we introduce a novel triplet learning strategy that explicitly models temporal differences, which are crucial to the CD task. Furthermore, random spatial and spectral perturbations are introduced during training to enhance robustness to temporal noise. In addition, a grid sparsity regularization is defined to suppress insignificant changes, and an IoU-matching algorithm is developed to refine the CD results. Experiments on three benchmark CD datasets demonstrate that the proposed S2C learning framework achieves significant improvements in accuracy, surpassing current state-of-the-art by over 31%, 9% and 23%, respectively. It also demonstrates robustness and sample efficiency, suitable for training and adaptation of various VFMs or backbone neural networks.

PDF Details DOI

EAAI Journal 2025 Journal Article

A multiple convolution and bilayer acceleration model for precise and efficient early urban fire detection in complex scenarios

Pei Shi
Jun Lu
Yachen Xu
Quan Wang
Yonghong Zhang
Liang Kuang
Deji Chen
Guangyan Huang

AI advancement enables earlier and more effective urban fire detection, crucial for slowing fire spread. However, hardware limitations make precise and efficient detection under limited resources a major challenge. Moreover, earlier detection of fire requires the identification of smoke, which further exacerbates the difficulty of detecting algorithms since smoke's inherent low-contrast visual properties produce feature blurring from the surrounding background. In this paper, we propose a novel multiple convolutions and bilayer accelerate (MCBA) model for effective early urban fire detection in terms of precision, lightweight and efficiency, which takes advantage of the mainstream You Only Look Once version 8 (YOLOv8) to training and testing the early fire detection model. In our MCBA model, three optimization techniques have been developed to balance lightweight and precision. First, it designs a new multi-convolution (MC) structure to reduce the size of the original backbone network by avoiding complex or skipping connections. Second, the model includes a novel design of a bilayer accelerate mechanism (BAM) at the neck to minimize the interference of redundant background information in multiple scenarios. Third, we provide a precision compensation strategy (PCS) at the neck to enhance the feature extraction and aggregation capabilities, enabling effective detection of small fire areas. The experiments demonstrate that our proposed MCBA model achieves higher performance in terms of precision and efficiency compared with 17 counterpart detection models. It exhibits superior performance with minimal parameter count and the lowest computational complexity among the compared methods. The model shows strong potential for deployment in early urban fire detection across a variety of real-world scenarios.

Details DOI

AAAI Conference 2025 Conference Paper

DepMGNN: Matrixial Graph Neural Network for Video-based Automatic Depression Assessment

Zijian Wu
Leijing Zhou
Shuanglin Li
Changzeng Fu
Jun Lu
Jing Han
Yi Zhang
Zhuang Zhao

Depression can be reflected by long-term human spatio-temporal facial behaviours. While human face videos recorded in real-world usually have long and variable lengths, existing video-based depression assessment approaches frequently re-sample/down-sample such videos to short and equal-length videos, or split each video into several equal-length segments, where segment-level spatio-temporal facial behaviours are suppressed as a vector-style representations for RNN-based long-term (video-level) modelling. Both strategies lead to crucial information loss and distortion. In this paper, we propose a novel graph-style data structure called Matrixial Graph and an effective Matrixial Graph Neural Network (MGNN) for face video-based depression assessment, which can directly and end-to-end model long-term depression-specific spatio-temporal facial cues from variable-length videos without resampling/splitting videos or suppressing video segments to vectors. Importantly, the nodes in our matrixial graph are capable of including matrices of different shapes, and thus nodes of a matrix graph can directly represent all frame-level 2D facial feature maps (or images themselves) of an entire video regardless of its length. Then, our MGNN is the first GNN that can jointly process matrixial graphs containing varying numbers of nodes, which further learns matrix-style edge features, thereby facilitating to explicit model video-level multi-scale spatio-temporal facial behaviours among matrixial graph nodes for depression assessment. Experiments show that the explicit spatio-temporal modeling on 2D facial feature maps, facilitated by our matrixial graph/MGNN, provided significant benefits, leading our approach to achieve new state-of-the-art performances on AVEC2013 and AVEC2014 datasets with large advantages.

PDF Details DOI

YNIMG Journal 2025 Journal Article

Potential separation of multiple system atrophy and Parkinson’s disease by susceptibility-derived components

Su Yan
Jun Lu
Bingfang Duan
Shun Zhang
Dong Liu
Yuanyuan Qin
Alexey V. Dimov
Junghun Cho

BACKGROUND: Substantial evidence emphasizes the dysregulation of iron homeostasis, demyelination and oxidative stress in the neurodegenerative process of multiple system atrophy (MSA) and Parkinson's disease (PD), although its clinical implications remain unclear. Recent MRI post-processing techniques leveraging magnetic susceptibility properties provide a noninvasive means to characterize iron, myelin content and oxygen metabolism alterations. This study aims to investigate subcortical alterations of susceptibility-derived metrics in these two synucleinopathies. METHODS: A cohort comprising 180 patients (122 with PD and 58 with MSA) and 77 healthy controls (HCs) underwent clinical evaluation and multi-echo gradient echo MRI scans. Susceptibility source separation, susceptibility-based oxygen extraction fraction (OEF) mapping and semiautomatic subcortical nuclei segmentation were utilized to derive parametric values of deep gray matter in all subjects. RESULTS: MSA patients showed markedly elevated paramagnetic susceptibility values in the putamen, globus pallidus (GP) and thalamus; increased diamagnetic susceptibility values in the putamen and dentate nucleus; and reduced OEF values across all nuclei compared with PD patients and HCs. Whereas PD exhibited increased positive susceptibility values in the substantia nigra and enhancing negative values in the GP, similar to MSA. Notably, age-related reductions in OEF were evident in HCs, which was altered by the MSA pathology. Paramagnetic susceptibility was correlated with disease severity. Moreover, the susceptibility-derived metrics of striatum and midbrain nuclei proved to be effective predictors to distinguish PD from MSA (AUC = 0.833). CONCLUSION: Susceptibility-derived metrics could detect pathological involvement distinct to each disease, offering significant potential for differentiating between MSA and PD in clinical settings.

Details DOI

YNICL Journal 2025 Journal Article

State-specific GluCEST alterations in insular subregions are associated with depression and plasma inflammatory biomarker levels in patients with inflammatory bowel disease

Lixue Xu
Jun Lu
Minsi Zhou
Haiyun Shi
Jing Zheng
Tianxin Cheng
Hui Xu
Dawei Yang

BACKGROUND: Depression commonly co-occurs with inflammatory bowel disease (IBD). Abnormal glutamate levels in the insula and altered plasma inflammatory biomarkers are observed in IBD and depression. However, the changes in glutamate concentrations in insular subregions in IBD and their relationship with depression and inflammatory markers remain unclear. This study aimed to investigate differences in glutamate concentrations in insular subregions between IBD patients and healthy controls (HCs) and their correlation with depression scores and inflammatory markers. METHODS: Forty-two IBD patients (19 active, IBD-A; 23 in remission, IBD-R) and 46 HCs underwent glutamate chemical exchange saturation transfer (GluCEST) magnetic resonance imaging. Blood samples from 37 IBD patients were collected for plasma inflammatory biomarker analysis. GluCEST indices in insular subregions were measured. The Hospital Anxiety and Depression Scale (HADS-D) was used to estimate depression symptoms. Whole-brain voxel-based analysis using one-way ANOVA explored between-group differences in GluCEST indices within the insula. FDR-corrected partial correlation analysis evaluated the relationships between GluCEST, depression symptoms, and inflammatory factors. RESULTS: GluCEST indices decreased in IBD patients in the left dorsal dysgranular subregion of the insula (dId) (uncorrected p < 0.001, cluster-level FWE-corrected p < 0.05). GluCEST indices in the left dId showed a significant positive correlation with HADS-D in IBD-R (FDR corrected q < 0.05). Additionally, GluCEST indices in the left dId were negatively correlated with CXCL9 (FDR corrected q < 0.05). CONCLUSION: State-specific GluCEST alterations in the left dId are a cerebral metabolic feature of IBD. These changes are associated with depression and inflammatory biomarkers, suggesting that the brain-immune-gut axis might underlie depression in IBD patients.

Details DOI

EAAI Journal 2023 Journal Article

Real-time segmentation network for accurate weld detection in large weldments

Zijian Wu
Peng Gao
Jing Han
Lianfa Bai
Jun Lu
Zhuang Zhao

Aiming at the defects of inaccurate weld extraction and high matching error rate in automatic welding system of large weldments currently. We propose a multi task detection model based on CNN architecture, which integrates the semantic segmentation technology required for weldment merging as well as the edge detection technology needed for weld matching. In particular, for the purpose of predicting smoother edges and welds, we carefully construct a new segment head, which adopts the sub-pixel convolution technology for up-sampling. Furthermore, a joint optimization loss function is explored to alleviate the imbalance of category distribution in large-scale weldment datasets. To verify the effectiveness of the model, abundant groups of data are collected for training and testing. The experimental results indicate that the proposed method has achieved the optimal trade-off between detection accuracy (83. 35% mIoU, 95. 15% F-score of welds and edges) as well as speed (74FPS) on a 2080Ti GPU compared with other state-of-the-arts, which greatly improves the robustness of the automatic welding system for large weldments.

Details DOI

IJCAI Conference 2021 Conference Paper

Domain Generalization under Conditional and Label Shifts via Variational Bayesian Inference

Xiaofeng Liu
Bo Hu
Linghao Jin
Xu Han
Fangxu Xing
Jinsong Ouyang
Jun Lu
Georges El Fakhri

In this work, we propose a domain generalization (DG) approach to learn on several labeled source domains and transfer knowledge to a target domain that is inaccessible in training. Considering the inherent conditional and label shifts, we would expect the alignment of p(x|y) and p(y). However, the widely used domain invariant feature learning (IFL) methods relies on aligning the marginal concept shift w. r. t. p(x), which rests on an unrealistic assumption that p(y) is invariant across domains. We thereby propose a novel variational Bayesian inference framework to enforce the conditional distribution alignment w. r. t. p(x|y) via the prior distribution matching in a latent space, which also takes the marginal label shift w. r. t. p(y) into consideration with the posterior alignment. Extensive experiments on various benchmarks demonstrate that our framework is robust to the label shift and the cross-domain accuracy is significantly improved, thereby achieving superior performance over the conventional IFL counterparts.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis

Xiaofeng Liu
Xiongchang Liu
Bo Hu
Wenxuan Ji
Fangxu Xing
Jun Lu
Jane You
C.-C. Jay Kuo

Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the closeness of cross-domain class centroids. However, the cross-domain inner-class compactness and the underlying fine-grained subtype structure remained largely underexplored. In this work, we propose to adaptively carry out the fine-grained subtype-aware alignment by explicitly enforcing the class-wise separation and subtype-wise compactness with intermediate pseudo labels. Our key insight is that the unlabeled subtypes of a class can be divergent to one another with different conditional and label shifts, while inheriting the local proximity within a subtype. The cases with or without the prior information on subtype numbers are investigated to discover the underlying subtype structure in an online fashion. The proposed subtype-aware dynamic UDA achieves promising results on a medical diagnosis task.

PDF Details

AAAI Conference 2020 Conference Paper

Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training

Xiaofeng Liu
Yuzhuo Han
Song Bai
Yi Ge
Tianxing Wang
Xu Han
Site Li
Jane You

Semantic segmentation (SS) is an important perception manner for self-driving cars and robotics, which classiﬁes each pixel into a pre-determined class. The widely-used cross entropy (CE) loss-based deep networks has achieved signiﬁcant progress w. r. t. the mean Intersection-over Union (mIoU). However, the cross entropy loss can not take the different importance of each class in an self-driving system into account. For example, pedestrians in the image should be much more important than the surrounding buildings when make a decisions in the driving, so their segmentation results are expected to be as accurate as possible. In this paper, we propose to incorporate the importance-aware inter-class correlation in a Wasserstein training framework by conﬁguring its ground distance matrix. The ground distance matrix can be pre-deﬁned following a priori in a speciﬁc task, and the previous importance-ignored methods can be the particular cases. From an optimization perspective, we also extend our ground metric to a linear, convex or concave increasing function w. r. t. pre-deﬁned ground distance. We evaluate our method on CamVid and Cityscapes datasets with different backbones (SegNet, ENet, FCN and Deeplab) in a plug and play fashion. In our extenssive experiments, Wasserstein loss demonstrates superior segmentation performance on the predeﬁned critical classes for safe-driving.

PDF Details

ICRA Conference 2014 Conference Paper

Shortest paths through 3-dimensional cluttered environments

Jun Lu
Yancy Diaz-Mercado
Magnus Egerstedt
Haomin Zhou 0001
Shui-Nee Chow

This paper investigates the problem of finding shortest paths through 3-dimensional cluttered environments. In particular, an algorithm is presented that determines the shortest path between two points in an environment with obstacles which can be implemented on robots with capabilities of detecting obstacles in the environment. As knowledge of the environment is increasing while the vehicle moves around, the algorithm provides not only the global minimizer — or shortest path — with increasing probability as time goes by, but also provides a series of local minimizers. The feasibility of the algorithm is demonstrated on a quadrotor robot flying in an environment with obstacles.

Details

IROS Conference 2009 Conference Paper

Development and sensitivity analysis of a portable calibration system for joint offset of industrial robot

Yong Liu
Ning Xi 0001
Jianguo Zhao
Erick Nieves-Rivera
Yunyi Jia
Bingtuan Gao
Jun Lu

This paper describes our updated system for industrial robot joint offset calibration. The system consists of an IRB1600 industrial robot, a laser tool attached to the robot's end-effector, a portable position-sensitive device (PPD), and a PC based controller. By aiming the laser spot to the center of position-sensitive-detector (PSD) on the PPD with different robot configurations, the developed system ideally implements our proposed calibration method called the virtual line-based single-point constraint approach. However, unlike our previous approach, the calibration method is extended to identify the offset parameters with an uncalibrated laser tool. The position errors of the PPD and the sensitivities of error in the PSD plane to the variation of joint angles are analyzed. Two different robot configuration patterns are compared by implementing the calibration method. Both simulation and real experimental results are consistent with the mathematical analysis. Experimental results with small (10 −3 −10 −2 ) mean and standard deviation of parameters error verify the effectiveness of both the sensitivity analysis and the developed system.

Details