Yichen Liu

Yichen Liu

Auto-generated profile, based on publicly available information

Yichen Liu

Xidian University

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
6 January 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
SZShenlu Zhao
Shenlu Zhao
YLYichen Liu
Yichen Liu
QJQiang Jiao
Qiang Jiao
QZQiang Zhang
Qiang Zhang
JHJungong Han
Jungong Han
Semantic segmentation models gain robustness against adverse illumination conditions by taking advantage of complementary information from visible and thermal infrared (RGB-T) images. Despite its importance, most existing RGB-T semantic segmentation models directly adopt primitive fusion strategies, such as elementwise summation, to integrate multimodal features. Such strategies, unfortunately, overlook the modality discrepancies caused by inconsistent unimodal features obtained by two independent feature extractors, thus hindering the exploitation of cross-modal complementary information within the multimodal data. For that, we propose a novel network for RGB-T semantic segmentation, i.e. MDRNet $+$ , which is an improved version of our previous work ABMDRNet. The core of MDRNet $+$ is a brand new idea, termed the strategy of bridging-then-fusing, which mitigates modality discrepancies before cross-modal feature fusion. Concretely, an improved Modality Discrepancy Reduction (MDR $+$ ) subnetwork is designed, which first extracts unimodal features and reduces their modality discrepancies. Afterward, discriminative multimodal features for RGB-T semantic segmentation are adaptively selected and integrated via several channel-weighted fusion (CWF) modules. Furthermore, a multiscale spatial context (MSC) module and a multiscale channel context (MCC) module are presented to effectively capture the contextual information. Finally, we elaborately assemble a challenging RGB-T semantic segmentation dataset, i.e., RTSS, for urban scene understanding to mitigate the lack of well-annotated training data. Comprehensive experiments demonstrate that our proposed model surpasses other state-of-the-art models on the MFNet, PST900, and RTSS datasets remarkably.

4 September 2025 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
YLYichen Liu
Yichen Liu
ZQZhiqiang Qu
Zhiqiang Qu
Guo ZhengGuo Zheng
Guo Zheng
YJYe Junjie
Ye Junjie
Accurate power line detection is critical for unmanned aerial vehicle (UAV)-based inspection systems. However, the detection accuracy is severely compromised by visually complex backgrounds characterized by similar textures and environmental interference, which often lead to substantial false-positives and false-negatives in detection results. To address these limitations, we propose a novel Uncertainty Region Modeling and Calibration Network (URMCNet), which incorporates an Uncertainty Region Modeling and Calibration Strategy that explicitly models and calibrates regions prone to false positives and false negatives, so as to enhance the accuracy of power line detection. The core component of URMCNet is the Primary Feature Calibration Mechanism, which incorporates the False-Positive Region Suppression Module and the False-Negative Region Compensation Module. These two modules adaptively calibrate uncertain regions, thereby making the feature representation more accurate and comprehensive. Furthermore, we introduce a High-Frequency Aware Fusion Decoder, which effectively restores the fine-grained details, thereby guaranteeing the continuity of the prediction results. The comprehensive experimental results demonstrate that URMCNet significantly outperforms state-of-the-art methods on several key performance metrics on the publicly available VITLD and TTPLA datasets.

1 January 2026 in IEEE Sensors Journal
Verified
Journal Article
Closed access
YTYe Tao
Ye Tao
JZJuanjuan Zhu
Juanjuan Zhu
XZXiaofei Zhang
Xiaofei Zhang
YLYichen Liu
Yichen Liu
WHWangpeng He
Wangpeng He

10 May 2022 in arXiv
Verified
Preprint
Open access
PDF file
TLTingle Li
Tingle Li
YLYichen Liu
Yichen Liu
AOAndrew Owens
Andrew Owens
HZHang Zhao
Hang Zhao
From the patter of rain to the crunch of snow, the sounds we hear often convey the visual textures that appear within a scene. In this paper, we present a method for learning visual styles from unlabeled audio-visual data. Our model learns to manipulate the texture of a scene to match a sound, a problem we term audio-driven image stylization. Given a dataset of paired audio-visual data, we learn to modify input images such that, after manipulation, they are more likely to co-occur with a given input sound. In quantitative and qualitative evaluations, our sound-based model outperforms label-based approaches. We also show that audio can be an intuitive representation for manipulating images, as adjusting a sound's volume or mixing two sounds together results in predictable changes to visual style. Project webpage: https://tinglok.netlify.app/files/avstyle

1 January 2026 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YLYichen Liu
Yichen Liu
WZWenxuan Zhang
Wenxuan Zhang
XCXuanrui Chen
Xuanrui Chen
ZMZhao Ma
Zhao Ma
JYJunjie Ye
Junjie Ye
WHWei Hou
Wei Hou

1 January 2026 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
YLYichen Liu
Yichen Liu
XWXing Wang
Xing Wang
XCXuanrui Chen
Xuanrui Chen
Guo ZhengGuo Zheng
Guo Zheng
JYJunjie Ye
Junjie Ye