Publications (138)
Learning Locality-Constrained Collaborative Representation for Face Recognition
Xi Peng, Lei Zhang, Zhang Yi +1
The model of low-dimensional manifold and sparse representation are two well-known concise models that suggest each data can be described by a few characteristics. Manifold learnin…
Deep Sparse Subspace Clustering
Xi Peng, Jiashi Feng, Shijie Xiao +3
In this paper, we present a deep extension of Sparse Subspace Clustering, termed Deep Sparse Subspace Clustering (DSSC). Regularized by the unit sphere distribution assumption for…
Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention
Yuxiao Chen, Long Zhao, Xi Peng +2
We propose a Dynamic Graph-Based Spatial-Temporal Attention (DG-STA) method for hand gesture recognition. The key idea is to first construct a fully-connected graph from a hand ske…
Reconstruction-Based Disentanglement for Pose-invariant Face Recognition
Xi Peng, Xiang Yu, Kihyuk Sohn +2
Deep neural networks (DNNs) trained on large-scale datasets have recently achieved impressive improvements in face recognition. But a persistent challenge remains to develop method…
Cross-View Graph Consistency Learning for Invariant Graph Representations
Jie Chen, Hua Mao, Wai Lok Woo +2
Graph representation learning is fundamental for analyzing graph-structured data. Exploring invariant graph representations remains a challenge for most existing graph representati…
Rethinking Kernel Methods for Node Representation Learning on Graphs
Yu Tian, Long Zhao, Xi Peng +1
Graph kernels are kernel methods measuring graph similarity and serve as a standard tool for graph classification. However, the use of kernel methods for node classification, which…
High-Speed Dynamic 3D Imaging with Sensor Fusion Splatting
Zihao Zou, Ziyuan Qu, Xi Peng +3
Capturing and reconstructing high-speed dynamic 3D scenes has numerous applications in computer graphics, vision, and interdisciplinary fields such as robotics, aerodynamics, and e…
Semantic Invariant Multi-view Clustering with Fully Incomplete Information
Pengxin Zeng, Mouxing Yang, Yiding Lu +3
Robust multi-view learning with incomplete information has received significant attention due to issues such as incomplete correspondences and incomplete instances that commonly af…
Beyond Loss Values: Robust Dynamic Pruning via Loss Trajectory Alignment
Huaiyuan Qin, Muli Yang, Gabriel James Goenawan +5
Existing dynamic data pruning methods often fail under noisy-label settings, as they typically rely on per-sample loss as the ranking criterion. This could mistakenly lead to prese…
Test-time Adaptation for Cross-modal Retrieval with Query Shift
Haobin Li, Peng Hu, Qianjun Zhang +3
The success of most existing cross-modal retrieval methods heavily relies on the assumption that the given queries follow the same distribution of the source domain. However, such…
Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings
Yunxiang Peng, Mengmeng Ma, Ziyu Yao +1
Reliable generalization metrics are fundamental to the evaluation of machine learning models. Especially in high-stakes applications where labeled target data are scarce, evaluatio…
Adaptive Cascading Network for Continual Test-Time Adaptation
Kien X. Nguyen, Fengchun Qiao, Xi Peng
We study the problem of continual test-time adaption where the goal is to adapt a source pre-trained model to a sequence of unlabelled target domains at test time. Existing methods…
Automatic Health Problem Detection from Gait Videos Using Deep Neural Networks
Rahil Mehrizi, Xi Peng, Shaoting Zhang +2
The aim of this study is developing an automatic system for detection of gait-related health problems using Deep Neural Networks (DNNs). The proposed system takes a video of patien…
LaverNet: Lightweight All-in-one Video Restoration via Selective Propagation
Haiyu Zhao, Yiwen Shan, Yuanbiao Gou +1
Recent studies have explored all-in-one video restoration, which handles multiple degradations with a unified model. However, these approaches still face two challenges when dealin…
CU-Net: Coupled U-Nets
Zhiqiang Tang, Xi Peng, Shijie Geng +2
We design a new connectivity pattern for the U-Net architecture. Given several stacked U-Nets, we couple each U-Net pair through the connections of their semantic blocks, resulting…
RuntimeSlicer: Towards Generalizable Unified Runtime State Representation for Failure Management
Lingzhe Zhang, Tong Jia, Weijie Hong +9
Modern software systems operate at unprecedented scale and complexity, where effective failure management is critical yet increasingly challenging. Metrics, traces, and logs provid…
Robust Duality Learning for Unsupervised Visible-Infrared Person Re-Identification
Yongxiang Li, Yuan Sun, Yang Qin +3
Unsupervised visible-infrared person re-identification (UVI-ReID) aims to retrieve pedestrian images across different modalities without costly annotations, but faces challenges du…
FALCON: Scalable Reasoning over Inconsistent ALC Ontologies
Tilman Hinnerichs, Zhenwei Tang, Xi Peng +2
Ontologies are one of the richest sources of knowledge. Real-world ontologies often contain thousands of axioms and are often human-made. Hence, they may contain inconsistency and…
Robust Multi-view Clustering against Imperfect Information
Zhichao Huang, Haochen Zhou, Hao Wang +2
Real-world multi-view data always suffer from imperfect information problem, where the view-specific observations are absent (i.e., Incomplete Views, IV) and cross-view corresponde…
Backhaul-Aware Caching Placement for Wireless Networks
Xi Peng, Juei-Chin Shen, Jun Zhang +1
As the capacity demand of mobile applications keeps increasing, the backhaul network is becoming a bottleneck to support high quality of experience (QoE) in next-generation wireles…
Beyond Accuracy: On the Effects of Fine-tuning Towards Vision-Language Model's Prediction Rationality
Qitong Wang, Tang Li, Kien X. Nguyen +1
Vision-Language Models (VLMs), such as CLIP, have already seen widespread applications. Researchers actively engage in further fine-tuning VLMs in safety-critical domains. In these…
Toward Robust and Harmonious Adaptation for Cross-modal Retrieval
Haobin Li, Mouxing Yang, Xi Peng
Recently, the general-to-customized paradigm has emerged as the dominant approach for Cross-Modal Retrieval (CMR), which reconciles the distribution shift problem between the sourc…
Efficient Failure Management for Multi-Agent Systems with Reasoning Trace Representation
Lingzhe Zhang, Tong Jia, Mingyu Wang +9
Large Language Models (LLM)-based Multi-Agent Systems (MASs) have emerged as a new paradigm in software system design, increasingly demonstrating strong reasoning and collaboration…
You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network
Boyun Li, Yuanbiao Gou, Shuhang Gu +3
In this paper, we study two challenging and less-touched problems in single image dehazing, namely, how to make deep learning achieve image dehazing without training on the ground-…
Non-Hierarchical Transformers for Pedestrian Segmentation
Amani Kiruga, Xi Peng
We propose a methodology to address the challenge of instance segmentation in autonomous systems, specifically targeting accessibility and inclusivity. Our approach utilizes a non-…
Learning Subspace-Preserving Sparse Attention Graphs from Heterogeneous Multiview Data
Jie Chen, Yuanbiao Gou, Chuanbin Liu +2
The high-dimensional features extracted from large-scale unlabeled data via various pretrained models with diverse architectures are referred to as heterogeneous multiview data. Mo…
Test-Time Degradation Adaptation for Open-Set Image Restoration
Yuanbiao Gou, Haiyu Zhao, Boyun Li +2
In contrast to close-set scenarios that restore images from a predefined set of degradations, open-set image restoration aims to handle the unknown degradations that were unforesee…
High-Dimensional MR Reconstruction Integrating Subspace and Adaptive Generative Models
Ruiyang Zhao, Xi Peng, Varun A. Kelkar +2
We present a novel method that integrates subspace modeling with an adaptive generative image prior for high-dimensional MR image reconstruction. The subspace model imposes an expl…
Incomplete Multi-view Clustering via Prototype-based Imputation
Haobin Li, Yunfan Li, Mouxing Yang +3
In this paper, we study how to achieve two characteristics highly-expected by incomplete multi-view clustering (IMvC). Namely, i) instance commonality refers to that within-cluster…
Are Multimodal Transformers Robust to Missing Modality?
Mengmeng Ma, Jian Ren, Long Zhao +2
Multimodal data collected from the real world are often imperfect due to missing modalities. Therefore multimodal models that are robust against modal-incomplete data are highly pr…
RED-Net: A Recurrent Encoder-Decoder Network for Video-based Face Alignment
Xi Peng, Rogerio S. Feris, Xiaoyu Wang +1
We propose a novel method for real-time face alignment in videos based on a recurrent encoder-decoder network model. Our proposed model predicts 2D facial point heat maps regulariz…
Robust Domain Adaptation for Machine Reading Comprehension
Liang Jiang, Zhenyu Huang, Jia Liu +2
Most domain adaptation methods for machine reading comprehension (MRC) use a pre-trained question-answer (QA) construction model to generate pseudo QA pairs for MRC transfer. Such…
Semantic-Guided Multi-Attention Localization for Zero-Shot Learning
Yizhe Zhu, Jianwen Xie, Zhiqiang Tang +2
Zero-shot learning extends the conventional object classification to the unseen class recognition by introducing semantic representations of classes. Existing approaches predominan…
AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM
Haoyu Huang, Hong Ting Tsang, Jiaxin Bai +3
Retrieval-augmented generation (RAG) has shown some success in augmenting large language models (LLMs) with external knowledge. However, as a non-parametric knowledge integration p…
Hierarchical Sparse Representation Clustering for High-Dimensional Data Streams
Jie Chen, Hua Mao, Yuanbiao Gou +1
Data stream clustering reveals patterns within continuously arriving, potentially unbounded data sequences. Numerous data stream algorithms have been proposed to cluster data strea…
Multi-granularity Correspondence Learning from Long-term Noisy Videos
Yijie Lin, Jie Zhang, Zhenyu Huang +3
Existing video-language studies mainly focus on learning short video clips, leaving long-term temporal dependencies rarely explored due to over-high computational cost of modeling…
Constructing the L2-Graph for Robust Subspace Learning and Subspace Clustering
Xi Peng, Zhiding Yu, Huajin Tang +1
Under the framework of graph-based learning, the key to robust subspace clustering and subspace learning is to obtain a good similarity graph that eliminates the effects of errors…
Cache Size Allocation in Backhaul Limited Wireless Networks
Xi Peng, Jun Zhang, S. H. Song +1
Caching popular content at base stations is a powerful supplement to existing limited backhaul links for accommodating the exponentially increasing mobile data traffic. Given the l…
Deep learning-based estimation of whole-body kinematics from multi-view images
Kien X. Nguyen, Liying Zheng, Ashley L. Hawke +4
It is necessary to analyze the whole-body kinematics (including joint locations and joint angles) to assess risks of fatal and musculoskeletal injuries in occupational tasks. Human…
Improving Representation Learning of Complex Critical Care Data with ICU-BERT
Ricardo Santos, André V. Carreiro, Xi Peng +2
The multivariate, asynchronous nature of real-world clinical data, such as that generated in Intensive Care Units (ICUs), challenges traditional AI-based decision-support systems.…
Towards In-Depth Root Cause Localization for Microservices with Multi-Agent Recursion-of-Thought
Lingzhe Zhang, Tong Jia, Kangjin Wang +8
As modern microservice systems grow increasingly complex due to dynamic interactions and evolving runtime environments, they experience failures with rising frequency. Ensuring sys…
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora
Jiaxin Bai, Wei Fan, Qi Hu +17
We present AutoSchemaKG, a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. Our system leverages large language models t…
A Survey on Deep Clustering: From the Prior Perspective
Yiding Lu, Haobin Li, Yunfan Li +2
Facilitated by the powerful feature extraction ability of neural networks, deep clustering has achieved great success in analyzing high-dimensional and complex real-world data. The…
SeafloorAI: A Large-scale Vision-Language Dataset for Seafloor Geological Survey
Kien X. Nguyen, Fengchun Qiao, Arthur Trembanis +1
A major obstacle to the advancements of machine learning models in marine science, particularly in sonar imagery analysis, is the scarcity of AI-ready datasets. While there have be…
Tail Quantile Estimation for Non-preemptive Priority Queues
Jin Guang, Guiyu Hong, Xinyun Chen +4
Motivated by applications in computing and telecommunication systems, we investigate the problem of estimating p-quantile of steady-state sojourn times in a single-server multi-cla…
Provable Dynamic Fusion for Low-Quality Multimodal Data
Qingyang Zhang, Haitao Wu, Changqing Zhang +4
The inherent challenge of multimodal fusion is to precisely capture the cross-modal correlation and flexibly conduct cross-modal interaction. To fully release the value of each mod…
dugMatting: Decomposed-Uncertainty-Guided Matting
Jiawei Wu, Changqing Zhang, Zuoyong Li +3
Cutting out an object and estimating its opacity mask, known as image matting, is a key task in image and video editing. Due to the highly ill-posed issue, additional inputs, typic…
Uncertainty-guided Model Generalization to Unseen Domains
Fengchun Qiao, Xi Peng
We study a worst-case scenario in generalization: Out-of-domain generalization from a single source. The goal is to learn a robust model from a single source and expect it to gener…
Cartoonish sketch-based face editing in videos using identity deformation transfer
Long Zhao, Fangda Han, Xi Peng +4
We address the problem of using hand-drawn sketches to create exaggerated deformations to faces in videos, such as enlarging the shape or modifying the position of eyes or mouth. T…
Accelerated MR Elastography Using Learned Neural Network Representation
Xi Peng
To develop a deep-learning method for achieving fast high-resolution MR elastography from highly undersampled data without the need of high-quality training dataset. We first frame…
Next-Scale Prediction: A Self-Supervised Approach for Real-World Image Denoising
Yiwen Shan, Haiyu Zhao, Peng Hu +2
Self-supervised real-world image denoising remains a fundamental challenge, arising from the antagonistic trade-off between decorrelating spatially structured noise and preserving…
Robust Fuzzy Multi-view Learning under View Conflict
Siyuan Duan, Yuan Sun, Dezhong Peng +3
Trusted multi-view classification aims to deliver reliable fusion for accurate predictions and has recently attracted substantial attention in both academia and industry. However,…
Out-Of-Distribution Detection with Diversification (Provably)
Haiyun Yao, Zongbo Han, Huazhu Fu +3
Out-of-distribution (OOD) detection is crucial for ensuring reliable deployment of machine learning models. Recent advancements focus on utilizing easily accessible auxiliary outli…
PointCloud-Text Matching: Benchmark Datasets and a Baseline
Yanglin Feng, Yang Qin, Dezhong Peng +3
In this paper, we present and study a new instance-level retrieval task: PointCloud-Text Matching (PTM), which aims to identify the exact cross-modal instance that matches a given…
Quantized Densely Connected U-Nets for Efficient Landmark Localization
Zhiqiang Tang, Xi Peng, Shijie Geng +3
In this paper, we propose quantized densely connected U-Nets for efficient visual landmark localization. The idea is that features of the same semantic meanings are globally reused…
A Recurrent Encoder-Decoder Network for Sequential Face Alignment
Xi Peng, Rogerio S. Feris, Xiaoyu Wang +1
We propose a novel recurrent encoder-decoder network model for real-time video-based face alignment. Our proposed model predicts 2D facial point maps regularized by a regression lo…
Interpretable Failure Detection with Human-Level Concepts
Kien X. Nguyen, Tang Li, Xi Peng
Reliable failure detection holds paramount importance in safety-critical applications. Yet, neural networks are known to produce overconfident predictions for misclassified samples…
Connections Between Nuclear Norm and Frobenius Norm Based Representations
Xi Peng, Canyi Lu, Zhang Yi +1
A lot of works have shown that frobenius-norm based representation (FNR) is competitive to sparse representation and nuclear-norm based representation (NNR) in numerous tasks such…
Automatic Subspace Learning via Principal Coefficients Embedding
Xi Peng, Jiwen Lu, Zhang Yi +1
In this paper, we address two challenging problems in unsupervised subspace learning: 1) how to automatically identify the feature dimension of the learned subspace (i.e., automati…
Inductive Sparse Subspace Clustering
Xi Peng, Lei Zhang, Zhang Yi
Sparse Subspace Clustering (SSC) has achieved state-of-the-art clustering quality by performing spectral clustering over a -norm based similarity graph. However, SSC is a…
Multiview Self-Representation Learning across Heterogeneous Views
Jie Chen, Zhu Wang, Chuanbin Liu +1
Features of the same sample generated by different pretrained models often exhibit inherently distinct feature distributions because of discrepancies in the model pretraining objec…
Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation
Nathaniel Merrill, Yuliang Guo, Xingxing Zuo +5
We propose a keypoint-based object-level SLAM framework that can provide globally consistent 6DoF pose estimates for symmetric and asymmetric objects alike. To the best of our know…
A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts
Yizhe Zhu, Mohamed Elhoseiny, Bingchen Liu +2
Most existing zero-shot learning methods consider the problem as a visual semantic embedding one. Given the demonstrated capability of Generative Adversarial Networks(GANs) to gene…
Layered Group Sparse Beamforming for Cache-Enabled Green Wireless Networks
Xi Peng, Yuanming Shi, Jun Zhang +1
The exponential growth of mobile data traffic is driving the deployment of dense wireless networks, which will not only impose heavy backhaul burdens, but also generate considerabl…
Relationship Quantification of Image Degradations
Wenxin Wang, Boyun Li, Yuanbiao Gou +3
In this paper, we study two challenging but less-touched problems in image restoration, namely, i) how to quantify the relationship between image degradations and ii) how to improv…
Semantic Graph Convolutional Networks for 3D Human Pose Regression
Long Zhao, Xi Peng, Yu Tian +2
In this paper, we study the problem of learning Graph Convolutional Networks (GCNs) for regression. Current architectures of GCNs are limited to the small receptive field of convol…
Improving Distant Supervised Relation Extraction by Dynamic Neural Network
Yanjie Gou, Yinjie Lei, Lingqiao Liu +2
Distant Supervised Relation Extraction (DSRE) is usually formulated as a problem of classifying a bag of sentences that contain two query entities, into the predefined relation cla…
Multi-Scale Adaptive Network for Single Image Denoising
Yuanbiao Gou, Peng Hu, Jiancheng Lv +2
Multi-scale architectures have shown effectiveness in a variety of tasks thanks to appealing cross-scale complementarity. However, existing architectures treat different scale feat…
Learning to Forecast and Refine Residual Motion for Image-to-Video Generation
Long Zhao, Xi Peng, Yu Tian +2
We consider the problem of image-to-video translation, where an input image is translated into an output video containing motions of a single object. Recent methods for such proble…
Airy-Gaussian vortex beams in the fractional nonlinear-Schrödinger medium
Shangling He, Kangzhu Zhou, Boris A. Malomed +9
We address the propagation of vortex beams with the circular Airy-Gaussian shape in a (2+1)-dimensional optical waveguide modeled by the fractional nonlinear Schrodinger equation.…
DEAL: Disentangle and Localize Concept-level Explanations for VLMs
Tang Li, Mengmeng Ma, Xi Peng
Large pre-trained Vision-Language Models (VLMs) have become ubiquitous foundational components of other models and downstream tasks. Although powerful, our empirical results reveal…
ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge
Yijie Lin, Guofeng Ding, Haochen Zhou +3
Existing multimodal retrieval benchmarks largely emphasize semantic matching on daily-life images and offer limited diagnostics of professional knowledge and complex reasoning. To…
Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients
Mengmeng Ma, Tang Li, Xi Peng
Federated Learning is widely employed to tackle distributed sensitive data. Existing methods primarily focus on addressing in-federation data heterogeneity. However, we observed th…
Twin Contrastive Learning for Online Clustering
Yunfan Li, Mouxing Yang, Dezhong Peng +3
This paper proposes to perform online clustering by conducting twin contrastive learning (TCL) at the instance and cluster level. Specifically, we find that when the data is projec…
Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers
Tang Li, Yanlin Chen, Mengmeng Ma +1
Despite high accuracy, Vision Transformer (ViT) predictions can be driven by spurious cues, raising the need to understand their inner workings before safe deployment. Sparse autoe…
Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales
Tang Li, Mengmeng Ma, Xi Peng
Large pretrained foundation models demonstrate exceptional performance and, in some high-stakes applications, even surpass human experts. However, most of these models are currentl…
Conditional Distribution Learning for Graph Classification
Jie Chen, Hua Mao, Chuanbin Liu +2
Leveraging the diversity and quantity of data provided by various graph-structured data augmentations while preserving intrinsic semantic information is challenging. Additionally,…
Image Clustering with External Guidance
Yunfan Li, Peng Hu, Dezhong Peng +3
The core of clustering is incorporating prior knowledge to construct supervision signals. From classic k-means based on data compactness to recent contrastive clustering guided by…
RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation
Shuhao Yan, Changhao He, Xi Peng +1
Text-to-CAD generation translates natural-language design intent into editable and executable parametric computer-aided design (CAD) codes, reducing the expertise and effort requir…
DUDE: Diffusion-Based Unsupervised Cross-Domain Image Retrieval
Ruohong Yang, Peng Hu, Yunfan Li +1
Unsupervised cross-domain image retrieval (UCIR) aims to retrieve images of the same category across diverse domains without relying on annotations. Existing UCIR methods, which al…
Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition
Qitong Wang, Long Zhao, Liangzhe Yuan +2
We are concerned with a challenging scenario in unpaired multiview video learning. In this case, the model aims to learn comprehensive multiview representations while the cross-vie…
DiFiC: Your Diffusion Model Holds the Secret to Fine-Grained Clustering
Ruohong Yang, Peng Hu, Xi Peng +2
Fine-grained clustering is a practical yet challenging task, whose essence lies in capturing the subtle differences between instances of different classes. Such subtle differences…
Graph Matching with Bi-level Noisy Correspondence
Yijie Lin, Mouxing Yang, Jun Yu +3
In this paper, we study a novel and widely existing problem in graph matching (GM), namely, Bi-level Noisy Correspondence (BNC), which refers to node-level noisy correspondence (NN…
Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation
Xi Peng, Zhiqiang Tang, Fei Yang +2
Random data augmentation is a critical technique to avoid overfitting in training deep neural network models. However, data augmentation and network training are usually treated as…
Out-of-Domain Generalization from a Single Source: An Uncertainty Quantification Approach
Xi Peng, Fengchun Qiao, Long Zhao
We are concerned with a worst-case scenario in model generalization, in the sense that a model aims to perform well on many unseen domains while there is only one single domain ava…
Contrastive Clustering
Yunfan Li, Peng Hu, Zitao Liu +3
In this paper, we propose a one-stage online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning. To…
Stabilization of single- and multi-peak solitons in the fractional nonlinear Schroedinger equation with a trapping potential
Yunli Qiu, Boris A. Malomed, Dumitru Mihalache +3
We address the existence and stability of localized modes in the framework of the fractional nonlinear Schroedinger equation (FNSE) with the focusing cubic or focusing-defocusing c…
CR-GAN: Learning Complete Representations for Multi-view Generation
Yu Tian, Xi Peng, Long Zhao +2
Generating multi-view images from a single-view input is an essential yet challenging problem. It has broad applications in vision, graphics, and robotics. Our study indicates that…
A Unified Framework for Representation-based Subspace Clustering of Out-of-sample and Large-scale Data
Xi Peng, Huajin Tang, Lei Zhang +2
Under the framework of spectral clustering, the key of subspace clustering is building a similarity graph which describes the neighborhood relations among data points. Some recent…
dMAPAR-HMM: Reforming Traffic Model for Improving Performance Bound with Stochastic Network Calculus
Qingqing Yang, Xi Peng, Huiwen Yang +2
A popular branch of stochastic network calculus (SNC) utilizes moment-generating functions (MGFs) to characterize arrivals and services, which enables end-to-end performance analys…
Track Facial Points in Unconstrained Videos
Xi Peng, Qiong Hu, Junzhou Huang +1
Tracking Facial Points in unconstrained videos is challenging due to the non-rigid deformation that changes over time. In this paper, we propose to exploit incremental learning for…
LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification
Yiding Lu, Mouxing Yang, Dezhong Peng +3
Traditional text-based person ReID assumes that person descriptions from witnesses are complete and provided at once. However, in real-world scenarios, such descriptions are often…
Accelerated MRI Reconstruction with Separable and Enhanced Low-Rank Hankel Regularization
Xinlin Zhang, Hengfa Lu, Di Guo +5
The combination of the sparse sampling and the low-rank structured matrix reconstruction has shown promising performance, enabling a significant reduction of the magnetic resonance…
Multimodal Fusion on Low-quality Data: A Comprehensive Survey
Qingyang Zhang, Yake Wei, Zongbo Han +8
Multimodal fusion focuses on integrating information from multiple modalities with the goal of more accurate prediction, which has achieved remarkable progress in a wide range of s…
Propagation dynamics of the circular Airy Gaussian vortex beams in the fractional nonlinear Schrödinger equation
Shangling He, Kangzhu Zhou, Xi Peng +3
We have investigated the propagation dynamics of the circular Airy Gaussian vortex beams (CAGVBs) in a (2+1)-dimesional optical system discribed by fractional nonlinear Schrödinge…
Locally linear representation for image clustering
Liangli Zhen, Zhang Yi, Xi Peng +1
It is a key to construct a similarity graph in graph-oriented subspace learning and clustering. In a similarity graph, each vertex denotes a data point and the edge weight represen…
Scalable Global Alignment Graph Kernel Using Random Features: From Node Embedding to Graph Embedding
Lingfei Wu, Ian En-Hsu Yen, Zhen Zhang +5
Graph kernels are widely used for measuring the similarity between graphs. Many existing graph kernels, which focus on local patterns within graphs rather than their global propert…
Semantic-Consistent Bidirectional Contrastive Hashing for Noisy Multi-Label Cross-Modal Retrieval
Likang Peng, Chao Su, Wenyuan Wu +4
Cross-modal hashing (CMH) facilitates efficient retrieval across different modalities (e.g., image and text) by encoding data into compact binary representations. While recent meth…
Deep Learning for Spatiotemporal Modeling of Urbanization
Tang Li, Jing Gao, Xi Peng
Urbanization has a strong impact on the health and wellbeing of populations across the world. Predictive spatial modeling of urbanization therefore can be a useful tool for effecti…
Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization
Long Zhao, Yuxiao Wang, Jiaping Zhao +7
We introduce a novel representation learning method to disentangle pose-dependent as well as view-dependent factors from 2D human poses. The method trains a network using cross-vie…