activity
20192026
most citedLanguage Guided Local Infiltration for Interactive Image Retrieval

3 citations · 5 across the 13 of their papers we have counts for

collaborators

16 papers

cs.CV2026

Surgical Video Generation From Diffusion to World Models: A Survey

Fuxiang Huang, Chenxu Zhang, Liang Han +1

Surgical video data provides the primary training resource for models of intraoperative perception, surgical workflow understanding, and robotic decision-making. However, clinical…

cs.CR2026

Multimodal Reasoning with LLM for Encrypted Traffic Interpretation: A Benchmark

Longgang Zhang, Xiaowei Fu, Fuxiang Huang +1

Network traffic, as a key media format, is crucial for ensuring security and communications in modern internet infrastructure. While existing methods offer excellent performance, t…

cs.CR2026

Mean Masked Autoencoder with Flow-Mixing for Encrypted Traffic Classification

Xiao Liu, Xiaowei Fu, Fuxiang Huang +1

Network traffic classification using self-supervised pre-training models based on Masked Autoencoders (MAE) has demonstrated a huge potential. However, existing methods are confine…

cs.CV2026

Implicit Non-Causal Factors are Out via Dataset Splitting for Domain Generalization Object Detection

Zhilong Zhang, Lei Zhang, Qing He +3

Open world object detection faces a significant challenge in domain-invariant representation, i.e., implicit non-causal factors. Most domain generalization (DG) methods based on do…

cs.CV2026

Proxy Robustness in Vision Language Models is Effortlessly Transferable

Xiaowei Fu, Fuxiang Huang, Lei Zhang

As a pivotal technique for improving the defense of deep models, adversarial robustness transfer via distillation has demonstrated remarkable success in conventional image classifi…

cs.LG2025

Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm

Fuxiang Huang, Xiaowei Fu, Shiyu Ye +5

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a label-rich source domain to an unlabeled target domain by addressing domain shifts. Most UDA approaches empha…