Xiaoyuan Yu

Xiaoyuan Yu

Auto-generated profile, based on publicly available information

Xiaoyuan Yu

Macau University of Science and Technology, Macau, Macao

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 October 2024
Verified
Conference Paper
Open access
ALAjian Liu
Ajian Liu
HMHui Ma
Hui Ma
JZJunze Zheng
Junze Zheng
HYHaocheng Yuan
Haocheng Yuan
XYXiaoyuan Yu
Xiaoyuan Yu
ZLZhen Lei
Zhen Lei
In this work, borrowing a solution from the large-scale vision-language models (VLMs) instead of directly removing modality-specific signals from visual features, we propose a novel Flexible Modal CLIP (FM-CLIP) for flexible modal FAS, that can utilize text features to dynamically adjust visual features to be modality independent. In the visual branch, considering the huge visual differences of the same attack in different modalities, which makes it difficult for classifiers to flexibly identify subtle spoofing clues in different test modalities, we propose Cross-Modal Spoofing Enhancer (CMS-Enhancer). It includes a Frequency Extractor (FE) and Cross-Modal Interactor (CMI), aiming to map different modal attacks in a shared frequency space to reduce interference from modality-specific signals and enhance spoofing clues by leveraging cross-modal learning from the shared frequency space. In the text branch, we introduce a Language-Guided Patch Alignment (LGPA) based on prompt learning, which further guides the image encoder to focus on patch-level spoofing representations through dynamic weighting by text features. Thus, our FM-CLIP can flexibly test different modal samples by identifying and enhancing modality-agnostic spoofing cues. Finally, extensive experiments show that FM-CLIP is effective and outperforms state-of-the-art methods on multiple multi-modal datasets.

10 June 2022 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
XYXiaoyuan Yu
Xiaoyuan Yu
YLYanyan Liang
Yanyan Liang
Xuxin LinXuxin Lin
Xuxin Lin
JWJun Wan
Jun Wan
Tian WangTian Wang
Tian Wang
Hong-Ning DaiHong-Ning Dai
Hong-Ning Dai
Context prediction plays a crucial role in implementing autonomous driving applications. As one of important context-prediction tasks, crowd-and-vehicle counting is critical for achieving real-time traffic and crowd analysis, consequently facilitating decision-making processes for autonomous vehicles. However, the completion of crowd-and-vehicle counting also faces challenges, such as large-scale variations, imbalanced data distribution, and insufficient local patterns. To tackle these challenges, we put forth a novel frequency feature pyramid network (FFPNet) in this paper. Our proposed FFPNet extracts the multi-scale information by frequency feature pyramid module, which can tackle the issue of large-scale variations. Meanwhile, the frequency feature pyramid module uses different frequency branches to obtain different scale information. We also adopt the attention mechanism to strength the extraction of different scale information. Moreover, we devise a novel loss function, namely global-local consistency loss, to address the existing problems of imbalanced data distribution and insufficient local patterns. Furthermore, we conduct extensive experiments on six datasets to evaluate our proposed FFPNet. It is worth mentioning that we also construct a novel crowd-and-vehicle dataset (CROVEH), which is the only dataset that contains both crowd-and-vehicle annotations. The experimental results show that FFPNet achieves the best performance on different backbones, e.g., 52.69 mean absolute error (MAE) on P2PNet with FFP module. The codes are available at: https://github.com/MUST-AI-Lab/FFPNet .

1 January 2025 in IET Biometrics
Verified
Journal Article
Open access
YLYongze Li
Yongze Li
JGJing Gu
Jing Gu
NLNing Li
Ning Li
BLBo-Han Li
Bo-Han Li
XYXiaoyuan Yu
Xiaoyuan Yu
ZLZhen Lei
Zhen Lei
Unified face attack detection (UAD), which simultaneously addresses physical presentation attacks (PAs) and digital forgery attacks (DAs) with a vision‐language model, remains challenging due to the difficulty of effectively separating live and fake cues. The challenges mainly arise from two aspects: (1) text prompts are insufficiently aligned with visual features across layers, and (2) patch tokens containing live and fake cues often overlap, leading to ambiguous attribution and small decision margins. To address these problems, we propose a novel Layer‐wise Cue Alignment framework (LCA) that leverages textual features to extract both layer‐wise and global cues from patch tokens, and we further introduce a new training strategy to improve the separation of live and fake cues. Specifically, the layer‐wise prompts are obtained by the cue matching block (CMB), which matches textual features with patch embeddings at each transformer layer, and the layer‐level cues are injected into the visual features of each layer and further aggregated by the cue fusion block (CFB) to form comprehensive prompts that enhance the overall visual representation. Moreover, we design a complementary supervision mechanism (CSM) that suppresses forgery cues in live faces while enforcing mutual exclusivity between live and fake cues in attack samples to improve the reliability of cue separation. Extensive experiments on multiple benchmarks demonstrate that our framework achieves state‐of‐the‐art performance on most protocols of the datasets.

6 January 2026 in Neurocomputing
Verified
Journal Article
Closed access
JLJiayao Li
Jiayao Li
CCChak Fong Cheang
Chak Fong Cheang
XYXiaoyuan Yu
Xiaoyuan Yu
STSuigu Tang
Suigu Tang
ZDZhaolong Du
Zhaolong Du
QCQianxiang Cheng
Qianxiang Cheng