Publications (97)
A regularization-patching dual quaternion optimization method for solving the hand-eye calibration problem
Zhongming Chen, Chen Ling, Liqun Qi +1
The hand-eye calibration problem is an important application problem in robot research. Based on the 2-norm of dual quaternion vectors, we propose a new dual quaternion optimizatio…
Hinge Regression Trees and HRT-Boost: Newton-Optimized Oblique Learning for Compact Tabular Models
Hongyi Li, Jun Xu, Hong Yan
Learning high-quality oblique decision trees remains a significant challenge due to the discrete and non-convex nature of split optimization. We present the Hinge Regression Tree (…
RankGraph: Unified Heterogeneous Graph Learning for Cross-Domain Recommendation
Renzhi Wu, Junjie Yang, Li Chen +3
Cross-domain recommendation systems face the challenge of integrating fine-grained user and item relationships across various product domains. To address this, we introduce RankGra…
Joint Sparse Representations and Coupled Dictionary Learning in Multi-Source Heterogeneous Image Pseudo-color Fusion
Long Bai, Shilong Yao, Kun Gao +5
Considering that Coupled Dictionary Learning (CDL) method can obtain a reasonable linear mathematical relationship between resource images, we propose a novel CDL-based Synthetic A…
Unsupervised Domain Adaptation for Low-dose CT Reconstruction via Bayesian Uncertainty Alignment
Kecheng Chen, Jie Liu, Renjie Wan +4
Low-dose computed tomography (LDCT) image reconstruction techniques can reduce patient radiation exposure while maintaining acceptable imaging quality. Deep learning is widely used…
Variable T-Product and Zero-Padding Tensor Completion with Applications
Liqun Qi, Rui Yan, Ziyan Luo +2
The T-product method based upon Discrete Fourier Transformation (DFT) has found wide applications in engineering, in particular, in image processing. In this paper, we propose vari…
Superpixel Tensor Pooling for Visual Tracking using Multiple Midlevel Visual Cues Fusion
Chong Wu, Le Zhang, Jiawang Cao +1
In this paper, we propose a method called superpixel tensor pooling tracker which can fuse multiple midlevel cues captured by superpixels into sparse pooled tensor features. Our me…
RO-SVD: A Reconfigurable Hardware Copyright Protection Framework for AIGC Applications
Zhuoheng Ran, Muhammad A. A. Abdelgawad, Zekai Zhang +2
The dramatic surge in the utilisation of generative artificial intelligence (GenAI) underscores the need for a secure and efficient mechanism to responsibly manage, use and dissemi…
Statistical CSI-Based Distributed Precoding Design for OFDM-Cooperative Multi-Satellite Systems
Yafei Wang, Vu Nguyen Ha, Konstantinos Ntontin +4
This paper investigates the design of distributed precoding for multi-satellite massive MIMO transmissions. We first conduct a detailed analysis of the transceiver model, in which…
Test-time adaptation for image compression with distribution regularization
Kecheng Chen, Pingping Zhang, Tiexin Qin +3
Current test- or compression-time adaptation image compression (TTA-IC) approaches, which leverage both latent and decoder refinements as a two-step adaptation scheme, have potenti…
Tunable Two-Dimensional Electron Gas at the Interfaces of Ferroelectric Potassium Tantalate Niobates
Jiaxin Lv, Silan Li, Chenhao Duan +3
The heterointerfaces at complex oxides have emerged as a promising platform for discovering novel physical phenomena and advancing integrated sensing, storage, and computing techno…
CURSOR: Scalable Mixed-Order Hypergraph Matching with CUR Decomposition
Qixuan Zheng, Ming Zhang, Hong Yan
To achieve greater accuracy, hypergraph matching algorithms require exponential increases in computational resources. Recent kd-tree-based approximate nearest neighbor (ANN) method…
Orthonormal Product Quantization Network for Scalable Face Image Retrieval
Ming Zhang, Xuefei Zhe, Hong Yan
Existing deep quantization methods provided an efficient solution for large-scale image retrieval. However, the significant intra-class variations like pose, illumination, and expr…
Efficient algorithms for Tucker decomposition via approximate matrix multiplication
Maolin Che, Yimin Wei, Hong Yan
This paper develops fast and efficient algorithms for computing Tucker decomposition with a given multilinear rank. By combining random projection and the power scheme, we propose…
Orthogonal Nonnegative Tucker Decomposition
Junjun Pan, Michael K. Ng, Ye Liu +2
In this paper, we study the nonnegative tensor data and propose an orthogonal nonnegative Tucker decomposition (ONTD). We discuss some properties of ONTD and develop a convex relax…
Enhancing Performance and Scalability of Large-Scale Recommendation Systems with Jagged Flash Attention
Rengan Xu, Junjie Yang, Yifan Xu +17
The integration of hardware accelerators has significantly advanced the capabilities of modern recommendation systems, enabling the exploration of complex ranking paradigms previou…
Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows
Shikun Liu, Mufei Li, Dongqi Fu +5
Large language models increasingly serve as execution engines for agentic systems, yet they still consume context through a sequential text interface. This creates a mismatch with…
Efficient randomized algorithms for the fixed Tucker-rank problem of Tucker decomposition with adaptive shifts
Maolin Che, Yimin Wei, Chong Wu +1
Randomized numerical linear algebra is proved to bridge theoretical advancements to offer scalable solutions for approximating tensor decomposition. This paper introduces fast rand…
Minimax principle for right eigenvalues of dual quaternion matrices and their generalized inverses
Chen Ling, Liqun Qi, Hong Yan
Dual quaternions can represent rigid body motion in 3D spaces, and have found wide applications in robotics, 3D motion modelling and control, and computer graphics. In this paper,…
Bi-level Unbalanced Optimal Transport for Partial Domain Adaptation
Zi-Ying Chen, Chuan-Xian Ren, Hong Yan
Partial domain adaptation (PDA) problem requires aligning cross-domain samples while distinguishing the outlier classes for accurate knowledge transfer. The widely used weighting f…
Learning Kernel for Conditional Moment-Matching Discrepancy-based Image Classification
Chuan-Xian Ren, Pengfei Ge, Dao-Qing Dai +1
Conditional Maximum Mean Discrepancy (CMMD) can capture the discrepancy between conditional distributions by drawing support from nonlinear kernel functions, thus it has been succe…
DTR: A Unified Deep Tensor Representation Framework for Multimedia Data Recovery
Ting-Wei Zhou, Xi-Le Zhao, Jian-Li Wang +4
Recently, the transform-based tensor representation has attracted increasing attention in multimedia data (e.g., images and videos) recovery problems, which consists of two indispe…
SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training
Hong Yan, Yang Liu, Yushen Wei +3
Skeleton sequence representation learning has shown great advantages for action recognition due to its promising ability to model human joints and topology. However, the current me…
Domain Generalization with Small Data
Kecheng Chen, Elena Gal, Hong Yan +1
In this work, we propose to tackle the problem of domain generalization in the context of \textit{insufficient samples}. Instead of extracting latent feature embeddings based on de…
Backward Errors and Small Sample Condition Estimation for -Sylveter Equations
Huai-An Diao, Hong Yan, Eric King-wah Chu
In this paper, we adopt a componentwise perturbation analysis for -Sylvester equations. Based on the small condition estimation (SCE), we devise the algorithms to estimate n…
Tuning the diffusion of magnon in Y3Fe5O12 by light excitation
Shuanhu Wang, Gang Li, Erjia Guo +11
Deliberate control of magnon transportation will lead to an energy-efficient technology for information transmission and processing. Y3Fe5O12(YIG), exhibiting extremely large magno…
Deep Signature: Characterization of Large-Scale Molecular Dynamics
Tiexin Qin, Mengxu Zhu, Chunyang Li +3
Understanding protein dynamics are essential for deciphering protein functional mechanisms and developing molecular therapies. However, the complex high-dimensional dynamics and in…
RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendation
Renzhi Wu, Zikun Cui, Junjie Yang +10
Graph-based retrieval at billion-node scale requires jointly solving three tightly coupled problems -- graph construction, representation learning, and real-time serving -- yet exi…
KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing
Mufei Li, Shikun Liu, Dongqi Fu +5
Post-hoc context erasing over the KV cache is challenging because a local edit has a global consequence: once a span has been processed, its influence propagates into the cached st…
DSDFormer: An Innovative Transformer-Mamba Framework for Robust High-Precision Driver Distraction Identification
Junzhou Chen, Zirui Zhang, Jing Yu +5
Driver distraction remains a leading cause of traffic accidents, posing a critical threat to road safety globally. As intelligent transportation systems evolve, accurate and real-t…
Unsupervised Domain Adaptation via Discriminative Manifold Propagation
You-Wei Luo, Chuan-Xian Ren, Dao-Qing Dai +1
Unsupervised domain adaptation is effective in leveraging rich information from a labeled source domain to an unlabeled target domain. Though deep learning and adversarial strategy…
How many integrals should be evaluated at least in two-dimensional hyperinterpolation?
Maolin Che, Congpei An, Yimin Wei +1
This paper introduces a novel approach to approximating continuous functions over high-dimensional hypercubes by integrating matrix CUR decomposition with hyperinterpolation techni…
Causal Reasoning Meets Visual Representation Learning: A Prospective Study
Yang Liu, Yushen Wei, Hong Yan +2
Visual representation learning is ubiquitous in various real-world applications, including visual comprehension, video understanding, multi-modal analysis, human-computer interacti…
Human Expression Recognition using Facial Shape Based Fourier Descriptors Fusion
Ali Raza Shahid, Sheheryar Khan, Hong Yan
Dynamic facial expression recognition has many useful applications in social networks, multimedia content analysis, security systems and others. This challenging process must be do…
Discriminative Residual Analysis for Image Set Classification with Posture and Age Variations
Chuan-Xian Ren, You-Wei Luo, Xiao-Lin Xu +2
Image set recognition has been widely applied in many practical problems like real-time video retrieval and image caption tasks. Due to its superior performance, it has grown into…
ChronoID: Infusing Explicit Temporal Signals into Semantic IDs for Generative Recommendation
Dongdong Nian, Dongqi Fu, Chenliang Xu +4
Semantic IDs are crucial in generative recommendation, but with a fundamental limitation: temporal information is not well incorporated into semantic IDs. Instead, time influences…
Generalizing to New Dynamical Systems via Frequency Domain Adaptation
Tiexin Qin, Hong Yan, Haoliang Li
Learning the underlying dynamics from data with deep neural networks has shown remarkable potential in modeling various complex physical dynamics. However, current approaches are c…
Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need
Kecheng Chen, Pingping Zhang, Hui Liu +6
We have recently witnessed that ``Intelligence" and `` Compression" are the two sides of the same coin, where the language large model (LLM) with unprecedented intelligence is a ge…
Interpretable and Reliable Detection of AI-Generated Images via Grounded Reasoning in MLLMs
Yikun Ji, Hong Yan, Jun Lan +5
The rapid advancement of image generation technologies intensifies the demand for interpretable and robust detection methods. Although existing approaches often attain high accurac…
Improved Deep Classwise Hashing With Centers Similarity Learning for Image Retrieval
Ming Zhang, Hong Yan
Deep supervised hashing for image retrieval has attracted researchers' attention due to its high efficiency and superior retrieval performance. Most existing deep supervised hashin…
Computing the -Spectral Radii of Uniform Hypergraphs with Applications
Jingya Chang, Weiyang Ding, Liqun Qi +1
The -spectral radius of a uniform hypergraph covers many important concepts, such as Lagrangian and spectral radius of the hypergraph, and is crucial for solving spectral extrem…
Code as Agent Harness
Xuying Ning, Katherine Tieu, Dongqi Fu +39
Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineerin…
One Dinomaly2 Detect Them All: A Unified Framework for Full-Spectrum Unsupervised Anomaly Detection
Jia Guo, Shuai Lu, Lei Fan +9
Unsupervised anomaly detection (UAD) has evolved from building specialized single-class models to unified multi-class models, yet existing multi-class models significantly underper…
Curvature-Informed Potential Energy Surface for Protein-Ligand Binding Affinity Prediction
Peng-Fei Sun, Chuan-Xian Ren, Hong Yan
Accurate prediction of protein-ligand binding affinity is essential for structure-based drug discovery. Recent geometric deep learning methods have achieved promising performance b…
UniFormer: Unified and Efficient Transformer for Reasoning Across General and Custom Computing
Zhuoheng Ran, Chong Wu, Renjie Xu +2
The success of neural networks such as convolutional neural networks (CNNs) has been largely attributed to their effective and widespread deployment on customised computing platfor…
Fuzzy SLIC: Fuzzy Simple Linear Iterative Clustering
Chong Wu, Jiangbin Zheng, Zhenan Feng +4
Most superpixel methods are sensitive to noise and cannot control the superpixel number precisely. To solve these problems, in this paper, we propose a robust superpixel method cal…
Computing The Analytic Connectivity of A Uniform Hypergraph
Chufeng Cui, Ziyan Luo, Liqun Qi +1
The analytic connectivity, proposed as a substitute of the algebraic connectivity in the setting of hypergraphs, is an important quantity in spectral hypergraph theory. The definit…
LU Decomposition and Generalized Autoone-Takagi Decomposition of Dual Matrices and their Applications
Renjie Xu, Yimin Wei, Hong Yan
This paper uses matrix transformations to provide the Autoone-Takagi decomposition of dual complex symmetric matrices and extends it to dual quaternion -Hermitian matrices. The…
Joint Learning of Deep Texture and High-Frequency Features for Computer-Generated Image Detection
Qiang Xu, Shan Jia, Xinghao Jiang +3
Distinguishing between computer-generated (CG) and natural photographic (PG) images is of great importance to verify the authenticity and originality of digital images. However, th…
Decoding ML Decision: An Agentic Reasoning Framework for Large-Scale Ranking System
Longfei Yun, Yihan Wu, Haoran Liu +11
Modern large-scale ranking systems operate within a sophisticated landscape of competing objectives, operational constraints, and evolving product requirements. Progress in this do…
Efficient RRT*-based Safety-Constrained Motion Planning for Continuum Robots in Dynamic Environments
Peiyu Luo, Shilong Yao, Yiyao Yue +3
Continuum robots, characterized by their high flexibility and infinite degrees of freedom (DoFs), have gained prominence in applications such as minimally invasive surgery and haza…
How much has the Sun influenced Northern Hemisphere temperature trends? An ongoing debate
Ronan Connolly, Willie Soon, Michael Connolly +20
To evaluate the role of Total Solar Irradiance (TSI) on Northern Hemisphere (NH) surface air temperature trends it is important to have reliable estimates of both quantities. 16 di…
Semantic Hierarchy Preserving Deep Hashing for Large-scale Image Retrieval
Ming Zhang, Xuefei Zhe, Le Ou-Yang +2
Deep hashing models have been proposed as an efficient method for large-scale similarity search. However, most existing deep hashing methods only utilize fine-level labels for trai…
ELFATT: Efficient Linear Fast Attention for Vision Transformers
Chong Wu, Maolin Che, Renjie Xu +2
The attention mechanism is the key to the success of transformers in different machine learning tasks. However, the quadratic complexity with respect to the sequence length of the…
Dual Quaternions and Dual Quaternion Vectors
Liqun Qi, Chen Ling, Hong Yan
We introduce a total order and the absolute value function for dual numbers. The absolute value function of dual numbers are with dual number values, and have properties similar to…
CWFBind: Geometry-Awareness for Fast and Accurate Protein-Ligand Docking
Liyan Jia, Chuan-Xian Ren, Hong Yan
Accurately predicting the binding conformation of small-molecule ligands to protein targets is a critical step in rational drug design. Although recent deep learning-based docking…
Graph Neural Network and Superpixel Based Brain Tissue Segmentation (Corrected Version)
Chong Wu, Zhenan Feng, Houwang Zhang +1
Convolutional neural networks (CNNs) are usually used as a backbone to design methods in biomedical image segmentation. However, the limitation of receptive field and large number…
An Interpretable Two-Stage Feature Decomposition Method for Deep Learning-based SAR ATR
Chenwei Wang, Renjie Xu, Congwen Wu +5
Synthetic aperture radar automatic target recognition (SAR ATR) has seen significant performance improvements with deep learning. However, the black-box nature of deep SAR ATR intr…
Elasticity -tensors and the Strong Ellipticity Condition
Weiyang Ding, Jinjie Liu, Liqun Qi +1
In this paper, we establish two sufficient conditions for the strong ellipticity of any fourth-order elasticity tensor and investigate a class of tensors satisfying the strong elli…
Partial Domain Adaptation via Importance Sampling-based Shift Correction
Cheng-Jun Guo, Chuan-Xian Ren, You-Wei Luo +2
Partial domain adaptation (PDA) is a challenging task in real-world machine learning scenarios. It aims to transfer knowledge from a labeled source domain to a related unlabeled ta…
PathOrchestra: A Comprehensive Foundation Model for Computational Pathology with Over 100 Diverse Clinical-Grade Tasks
Fang Yan, Jianfeng Wu, Jiawen Li +24
The complexity and variability inherent in high-resolution pathological images present significant challenges in computational pathology. While pathology foundation models leveragi…
Randomized algorithms for computing the tensor train approximation and their applications
Maolin Che, Yimin Wei, Hong Yan
In this paper, we focus on the fixed TT-rank and precision problems of finding an approximation of the tensor train (TT) decomposition of a tensor. Note that the TT-SVD and TT-cros…
Scalable Co-Clustering for Large-Scale Data through Dynamic Partitioning and Hierarchical Merging
Zihan Wu, Zhaoke Huang, Hong Yan
Co-clustering simultaneously clusters rows and columns, revealing more fine-grained groups. However, existing co-clustering methods suffer from poor scalability and cannot handle l…
Randomized algorithms for the low multilinear rank approximations of tensors
Maolin Che, Yimin Wei, Hong Yan
In this paper, we focus on developing randomized algorithms for the computation of low multilinear rank approximations of tensors based on the random projection and the singular va…
CTransformer: Deep-transformer-based 3D cell membrane tracking with subcellular-resolved molecular quantification
Zelin Li, Guoye Guan, Xiu Xian +13
Deep learning segmentation and fluorescence imaging techniques allow the cellular morphology of living embryos to be constructed spatiotemporally. These development processes invol…
Principled Synthetic Data Enables the First Scaling Laws for LLMs in Recommendation
Benyu Zhang, Qiang Zhang, Jianpeng Cheng +10
Large Language Models (LLMs) represent a promising frontier for recommender systems, yet their development has been impeded by the absence of predictable scaling laws, which are cr…
Locality-aware Private Class Identification for Domain Adaptation with Extreme Label Shift
Chuan-Xian Ren, Cheng-Jun Guo, Hong Yan
Domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain with different distributions. In real-world scenarios, the label spaces of t…
CMSL: Constructive Multi-Sequence Learning for Recommendation Systems
Zikun Cui, Renzhi Wu, Junjie Yang +10
Sequence learning has emerged as the promising paradigm in recommendation systems, surpassing traditional Deep Learning Recommendation Models (DLRM) by capturing the temporal nuanc…
CiUAV: A Multi-Task 3D Indoor Localization System for UAVs based on Channel State Information
Cunyi Yin, Chenwei Wang, Jing Chen +4
Accurate indoor positioning for unmanned aerial vehicles (UAVs) is critical for logistics, surveillance, and emergency response applications, particularly in GPS-denied environment…
Structuring and Tokenizing Distributed User Interest Context for Generative Recommendation
Ruizhong Qiu, Yinglong Xia, Dongqi Fu +6
Generative recommendation is an emerging paradigm that has shown promise in industrial recommendation systems, aiming to predict users' next interactions from their historical beha…
Learning Dynamic Graph Embeddings with Neural Controlled Differential Equations
Tiexin Qin, Benjamin Walker, Terry Lyons +2
This paper focuses on representation learning for dynamic graphs with temporal interactions. A fundamental issue is that both the graph structure and the nodes own their own dynami…
Learning with Signatures
J. de Curtò, I. de ZarzÃ, Hong Yan +1
In this work we investigate the use of the Signature Transform in the context of Learning. Under this assumption, we advance a supervised framework that potentially provides state-…
On Some Sufficient Conditions for Strong Ellipticity
Weiyang Ding, Liqun Qi, Hong Yan
We establish several sufficient conditions for the strong ellipticity of any fourth-order elasticity tensor in this paper. The first presented sufficient condition is an extension…
Synthetic Sandbox for Training Machine Learning Engineering Agents
Yuhang Zhou, Lizhu Zhang, Yifan Wu +4
As large language model agents advance beyond software engineering (SWE) tasks toward machine learning engineering (MLE), verifying agent behavior becomes orders of magnitude more…
VisAlgae 2023: A Dataset and Challenge for Algae Detection in Microscopy Images
Mingxuan Sun, Juntao Jiang, Zhiqiang Yang +21
Microalgae, vital for ecological balance and economic sectors, present challenges in detection due to their diverse sizes and conditions. This paper summarizes the second "Vision M…
Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact
Rizwan Qureshi, Ranjan Sapkota, Abbas Shah +16
Can machines truly think, reason and act in domains like humans? This enduring question continues to shape the pursuit of Artificial General Intelligence (AGI). Despite the growing…
Completely Positive Reformulations of Polynomial Optimization Problems with Linear Inequality Constraints
Haibin Chen, Hong Yan, Guanglu Zhou
Polynomial optimization encompasses a broad class of problems in which both the objective function and constraints are polynomial functions of the decision variables. In recent yea…
Test-time Adaptation for Foundation Medical Segmentation Model without Parametric Updates
Kecheng Chen, Xinyu Luo, Tiexin Qin +5
Foundation medical segmentation models, with MedSAM being the most popular, have achieved promising performance across organs and lesions. However, MedSAM still suffers from compro…
sparseGeoHOPCA: A Geometric Solution to Sparse Higher-Order PCA Without Covariance Estimation
Renjie Xu, Chong Wu, Maolin Che +3
We propose sparseGeoHOPCA, a novel framework for sparse higher-order principal component analysis (SHOPCA) that introduces a geometric perspective to high-dimensional tensor decomp…
Robustness in AI-Generated Detection: Enhancing Resistance to Adversarial Attacks
Sun Haoxuan, Hong Yan, Zhan Jiahui +6
The rapid advancement of generative image technology has introduced significant security concerns, particularly in the domain of face generation detection. This paper investigates…
YOLO advances to its genesis: a decadal and comprehensive review of the You Only Look Once (YOLO) series
Ranjan Sapkota, Marco Flores Calero, Rizwan Qureshi +9
This review systematically examines the progression of the You Only Look Once (YOLO) object detection algorithms from YOLOv1 to the recently unveiled YOLOv12. Employing a reverse c…
Soft-Masked Semi-Dual Optimal Transport for Partial Domain Adaptation
Yi-Ming Zhai, Chuan-Xian Ren, Hong Yan
Visual domain adaptation aims to learn discriminative and domain-invariant representation for an unlabeled target domain by leveraging knowledge from a labeled source domain. Parti…
Visual Causal Scene Refinement for Video Question Answering
Yushen Wei, Yang Liu, Hong Yan +2
Existing methods for video question answering (VideoQA) often suffer from spurious correlations between different modalities, leading to a failure in identifying the dominant visua…
Drug Supply Chain Optimization for Adaptive Clinical Trials
Jincheng Pang, Hong Yan, Zoe Hua
With increasing interest in adaptive clinical trial designs, challenges are present to drug supply chain management which may offset the benefit of adaptive designs. Thus, it is ne…
Towards Scalable Topological Regularizers
Hiu-Tung Wong, Darrick Lee, Hong Yan
Latent space matching, which consists of matching distributions of features in latent space, is a crucial component for tasks such as adversarial attacks and defenses, domain adapt…
Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval
Xuefei Zhe, Shifeng Chen, Hong Yan
Deep distance metric learning (DDML), which is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, has achieved encouraging…
A Quadratic Penalty Method for Hypergraph Matching
Chunfeng Cui, Qingna Li, Liqun Qi +1
Hypergraph matching is a fundamental problem in computer vision. Mathematically speaking, it maximizes a polynomial objective function, subject to assignment constraints. In this p…
Signature and Log-signature for the Study of Empirical Distributions Generated with GANs
Joaquim de Curtò, Irene de ZarzÃ, Hong Yan +1
In this paper, we bring forward the use of the recently developed Signature Transform as a way to measure the similarity between image distributions and provide detailed acquaintan…
Rapid Feature Extraction for Optical Character Recognition
M. Zahid Hossain, M. Ashraful Amin, Hong Yan
Feature extraction is one of the fundamental problems of character recognition. The performance of character recognition system is depends on proper feature extraction and correct…
Agentic Recommender System with Hierarchical Belief-State Memory
Xiang Shen, Yuhang Zhou, Yifan Wu +8
Memory-augmented LLM agents have advanced personalized recommendation, yet existing approaches universally adopt flat memory representations that conflate ephemeral signals with st…
BFLA: Block-Filtered Long-Context Attention Mechanism
Chong Wu, Zhenan Feng, Renjie Xu +5
This paper proposes Block-Filtered Long-Context Attention (BFLA), a training-free sparse prefill attention mechanism for long-context inference. BFLA adopts a two-stage design. In…
Domain Adaptation and Image Classification via Deep Conditional Adaptation Network
Pengfei Ge, Chuan-Xian Ren, Dao-Qing Dai +1
Unsupervised domain adaptation aims to generalize the supervised model trained on a source domain to an unlabeled target domain. Marginal distribution alignment of feature spaces i…
Instance segmentation with the number of clusters incorporated in embedding learning
Jianfeng Cao, Hong Yan
Semantic and instance segmentation algorithms are two general yet distinct image segmentation solutions powered by Convolution Neural Network. While semantic segmentation benefits…
Volume Tells: Dual Cycle-Consistent Diffusion for 3D Fluorescence Microscopy De-noising and Super-Resolution
Zelin Li, Chenwei Wang, Zhaoke Huang +4
3D fluorescence microscopy is essential for understanding fundamental life processes through long-term live-cell imaging. However, due to inherent issues in imaging principles, it…
YOLO-TS: Real-Time Traffic Sign Detection with Enhanced Accuracy Using Optimized Receptive Fields and Anchor-Free Fusion
Junzhou Chen, Heqiang Huang, Ronghui Zhang +4
Ensuring safety in both autonomous driving and advanced driver-assistance systems (ADAS) depends critically on the efficient deployment of traffic sign recognition technology. Whil…
Curvature-Guided Geometric Representation for Protein-Ligand Binding Affinity Prediction
Shuai Li, Chuan-Xian Ren, Yuhao Li +4
Protein-ligand binding affinity (PLA) prediction is critical in drug discovery. Despite the notable advancements in machine learning-based approaches, existing methods struggle to…
Deep Class-Wise Hashing: Semantics-Preserving Hashing via Class-wise Loss
Xuefei Zhe, Shifeng Chen, Hong Yan
Deep supervised hashing has emerged as an influential solution to large-scale semantic image retrieval problems in computer vision. In the light of recent progress, convolutional n…