4 citations · 8 across the 34 of their papers we have counts for
20 papers · 1 filter
Traffic-CBM: A Structurally Interpretable Multimodal Framework for Encrypted Traffic Classification
Honglei Jin, Wenshuo Chen, Shaofeng Liang +6
Encrypted traffic classification has achieved strong performance, but its decision process remains difficult to interpret. Existing methods usually combine flow statistics, packet…
MemoGen: Can Past Experience Improve Future Text-to-Image Generation?
Wenshuo Chen, Kuimou Yu, Bowen Tian +10
Modern text-to-image models have achieved strong visual synthesis, yet remain unreliable when prompts require implicit visual constraints, relational reasoning, or external knowled…
RadioFlow: Efficient Radio Map Construction Framework with Flow Matching
Haozhe Jia, Wenshuo Chen, Xiucheng Wang +8
Accurate and real-time radio map (RM) generation is crucial for next-generation wireless systems, yet diffusion-based approaches often suffer from large model sizes, slow iterative…
Concept Labels Are Not Enough: Rethinking Concept Bottleneck Models through Representation Integrity
Gaoxiang Huang, Songning Lai, Yutao Yue
Although deep neural networks achieve strong predictive performance, their internal reasoning often remains difficult to inspect and control. Concept Bottleneck Models (CBMs) addre…
LUMA: Low-Dimension Unified Motion Alignment with Dual-Path Anchoring for Text-to-Motion Diffusion Model
Haozhe Jia, Wenshuo Chen, Yuqi Lin +8
While current diffusion-based models, typically built on U-Net architectures, have shown promising results on the text-to-motion generation task, they still suffer from semantic mi…
VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results
Sizhuo Ma, Wei-Ting Chen, Qiang Gao +56
Face images play a crucial role in numerous applications; however, real-world conditions frequently introduce degradations such as noise, blur, and compression artifacts, affecting…
Da Yu: Towards USV-Based Image Captioning for Waterway Surveillance and Scene Understanding
Runwei Guan, Ningwei Ouyang, Tianhao Xu +10
Automated waterway environment perception is crucial for enabling unmanned surface vessels (USVs) to understand their surroundings and make informed decisions. Most existing waterw…
Stable Vision Concept Transformers for Medical Diagnosis
Lijie Hu, Songning Lai, Yuan Hua +3
Transparency is a paramount concern in the medical field, prompting researchers to delve into the realm of explainable AI (XAI). Among these XAI methods, Concept Bottleneck Models…
ANT: Adaptive Neural Temporal-Aware Text-to-Motion Model
Wenshuo Chen, Kuimou Yu, Haozhe Jia +8
While diffusion models advance text-to-motion generation, their static semantic conditioning ignores temporal-frequency demands: early denoising requires structural semantics for m…
IMTS is Worth Time Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction
Zhangyi Hu, Jiemin Wu, Hua Xu +5
Irregular Multivariate Time Series (IMTS) forecasting is challenging due to the unaligned nature of multi-channel signals and the prevalence of extensive missing data. Existing met…
Adaptive H&E-IHC information fusion staining framework based on feature extra
Yifan Jia, Xingda Yu, Zhengyang Ji +2
Immunohistochemistry (IHC) staining plays a significant role in the evaluation of diseases such as breast cancer. The H&E-to-IHC transformation based on generative models provides…
Physics-Informed Representation Alignment for Sparse Radio-Map Reconstruction
Haozhe Jia, Wenshuo Chen, Zhihui Huang +7
Radio map reconstruction is essential for enabling advanced applications, yet challenges such as complex signal propagation and sparse observational data hinder accurate reconstruc…
Free-T2M: Robust Text-to-Motion Generation for Humanoid Robots via Frequency-Domain
Wenshuo Chen, Haozhe Jia, Songning Lai +5
Enabling humanoid robots to synthesize complex, physically coherent motions from natural language commands is a cornerstone of autonomous robotics and human-robot interaction. Whil…
DRIVE: Dual-Robustness via Information Variability and Entropic Consistency in Source-Free Unsupervised Domain Adaptation
Ruiqiang Xiao, Songning Lai, Yijun Yang +3
Adapting machine learning models to new domains without labeled data, especially when source data is inaccessible, is a critical challenge in applications like medical imaging, aut…
CFSSeg: Closed-Form Solution for Class-Incremental Semantic Segmentation of 2D Images and 3D Point Clouds
Jiaxu Li, Rui Li, Jianyu Qi +8
2D images and 3D point clouds are foundational data types for multimedia applications, including real-time video analysis, augmented reality (AR), and 3D scene understanding. Class…
Towards Multi-dimensional Explanation Alignment for Medical Classification
Lijie Hu, Songning Lai, Wenshuo Chen +5
The lack of interpretability in the field of medical image analysis has significant ethical and legal implications. Existing interpretable methods in this domain encounter several…
Wolf2Pack: The AutoFusion Framework for Dynamic Parameter Fusion
Bowen Tian, Songning Lai, Yutao Yue
In the rapidly evolving field of deep learning, specialized models have driven significant advancements in tasks such as computer vision and natural language processing. However, t…
CAT: Concept-level backdoor ATtacks for Concept Bottleneck Models
Songning Lai, Jiayu Yang, Yu Huang +6
Despite the transformative impact of deep learning across multiple domains, the inherent opacity of these models has driven the development of Explainable Artificial Intelligence (…
Real-time Accident Anticipation for Autonomous Driving Through Monocular Depth-Enhanced 3D Modeling
Haicheng Liao, Yongkang Li, Chengyue Wang +7
The primary goal of traffic accident anticipation is to foresee potential accidents in real time using dashcam videos, a task that is pivotal for enhancing the safety and reliabili…
PEPL: Precision-Enhanced Pseudo-Labeling for Fine-Grained Image Classification in Semi-Supervised Learning
Bowen Tian, Songning Lai, Lujundong Li +4
Fine-grained image classification has witnessed significant advancements with the advent of deep learning and computer vision technologies. However, the scarcity of detailed annota…