Fuchang Liu

Dr. Fuchang Liu

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
11 March 2021 in IEEE Computer Graphics and Applications
Verified
Journal Article
Closed access
Yongwei MiaoYongwei Miao
Yongwei Miao
LZLei Zhang
Lei Zhang
JLJiazong Liu
Jiazong Liu
JWJinrong Wang
Jinrong Wang
FLFuchang Liu
Fuchang Liu
Shape completion for 3d point clouds is an important issue in the literature of computer graphics and computer vision. We propose an end-to-end shape-preserving point completion network through encoder-decoder architecture, which works directly on incomplete 3d point clouds and can restore their overall shapes and fine-scale structures. To achieve this task, we design a novel encoder which encodes information from neighboring points in different orientations and scales, as well as a decoder which outputs a dense and uniform complete point clouds. We augment 3d object dataset based on ModelNet40 and validate the effectiveness of our shape preserving completion network. Experimental results demonstrate that the recovered point clouds lie close to ground truth points. Our method outperforms state-of-the-art approaches in terms of Chamfer Distance (CD) error and Earth Mover's Distance (EMD) error. Furthermore, our end-to-end completion network is robust to model noise, the different levels of incomplete data, and can also generalize well to unseen objects and real-world data.

3 May 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
DZDibin Zhou
Dibin Zhou
HXHonggang Xu
Honggang Xu
WLWenhao Liu
Wenhao Liu
FLFuchang Liu
Fuchang Liu
With advancements in technology, lung nodule detection has significantly improved in both speed and accuracy. However, challenges remain in deploying these methods in complex real-world scenarios. This paper introduces an enhanced lung nodule detection algorithm base on RT-DETR, called LN-DETR. First, we designed a Deep and Shallow Detail Fusion layer that effectively fuses cross-scale features from both shallow and deep layers. Second, we optimized the computational load of the backbone network, effectively reducing the overall scale of the model. Finally, an efficient downsampling is designed to enhance the detection of lung nodules by re-weighting contextual information. Experiments conducted on the public LUNA16 dataset demonstrate that the proposed method, with a reduced number of parameters and computational overhead, achieves 83.7% mAP@0.5 and 36.3% mAP@0.5:0.95, outperforming RT-DETR in both model size and accuracy. These results highlight the superior detection accuracy of the proposed network while maintaining computational efficiency.

9 September 2021 in IEEE Access
Verified
Journal Article
Open access
LHLibin Hong
Libin Hong
XWXianglei Wu
Xianglei Wu
DZDibin Zhou
Dibin Zhou
FLFuchang Liu
Fuchang Liu
Automatic defect detection of light guide plates (LGPs) is an important task in the manufacture of liquid crystal displays. During thermo-printing, defects of tag lines on LGPs may occur easily, and these defects are of two categories: bubbles and missing tag lines. These defects lack salient visual attributes, such as edge-based and region-based features, and as such, traditional methods fail to detect them. To address this, we propose a Dense-bilinear convolutional neural network (BCNN), an end-to-end defect detection network, utilizing Dense-blocks (Huang et al. , 2017), Bilinear feature layers (Lin et al. , 2015), and squeeze-and-excitation blocks (Hu et al. , 2018). Our network exploits fine-grained texture features, which leads to parameter reduction and accuracy enhancement. We validate our network on our LGP dataset containing 5,860 images from three cases: bubbles, tag line existence, and tag line missing. Our network outperforms AlexNet (Krizhevsky et al. , 2012), VGG (Simonyan and Zisserman, 2014) and ResNet (He et al. , 2016), on both the public and our LGP datasets with less GPU memory consumption.

23 May 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JDJing Du
Jing Du
GXGuangtao Xu
Guangtao Xu
WLWenhao Liu
Wenhao Liu
DZDibin Zhou
Dibin Zhou
FLFuchang Liu
Fuchang Liu
As recent advancements in large language models enhance reasoning across various domains, educators are increasingly exploring their use in conversation-based tutoring systems. However, since LLMs are black-box models to users and lack human-like problem-solving strategies, users are hardly convinced by the answers provided by LLMs. This lack of trust can potentially undermine the effectiveness of learning in educational scenarios. To address these issues, we introduce a novel approach that integrates multi-agent debates into a lecture video Q&A system, aiming to assist computer science (CS) university students in self-learning by using LLMs to simulate debates between affirmative and negative debaters and a judge to reach a final answer and presenting the entire process to users for review. This approach is expected to lead to better learning outcomes and the improvement of students’ critical thinking. To validate the effectiveness of this approach, we carried out a user study through a prototype system and conducted preliminary experiments based on video lecture learning involving 90 CS students from three universities. The study compared different conditions and demonstrated that students who had access to a combination of video-based Q&A and multi-agent debates performed significantly better on quizzes compared to those who only had access to the video or video-based Q&A. These findings indicate that integrating multi-agent debates with lecture videos can substantially enhance the learning experience, which is also beneficial for the development of students’ high-order thinking abilities in the future.

28 August 2021 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
LHLibin Hong
Libin Hong
JWJohn Woodward
John Woodward
Ender ÖzcanEnder Özcan
Ender Özcan
FLFuchang Liu
Fuchang Liu
Genetic programming (GP) automatically designs programs. Evolutionary programming (EP) is a real-valued global optimisation method. EP uses a probability distribution as a mutation operator, such as Gaussian, Cauchy, or Lévy distribution. This study proposes a hyper-heuristic approach that employs GP to automatically design different mutation operators for EP. At each generation, the EP algorithm can adaptively explore the search space according to historical information. The experimental results demonstrate that the EP with adaptive mutation operators, designed by the proposed hyper-heuristics, exhibits improved performance over other EP versions (both manually and automatically designed). Many researchers in evolutionary computation advocate adaptive search operators (which do adapt over time) over non-adaptive operators (which do not alter over time). The core motive of this study is that we can automatically design adaptive mutation operators that outperform automatically designed non-adaptive mutation operators.

20 November 2019 in IEEE Access
Verified
Journal Article
Open access
XPXiang Pan
Xiang Pan
JLJie Lu
Jie Lu
FLFuchang Liu
Fuchang Liu
How to extract features of different shapes for style similarity evaluation is a very challenging research topic. Different from methods based on predefined style templates, we perform sparse learning and triplet embedding directly from the 3D shape local descriptors. The proposed method can adaptively generate element-level style features of different 3D patches for style similarity evaluation. The proposed algorithm mainly consists of the following steps. First, given a heterogeneous 3D shape collection, we learn mid-level style features by Siamese networks based on curvature-guided sampling directly on 3D shapes, which is a view-independent and part-independent approach. Second, we perform sparse coding to reduce the dimension of mid-level local features and achieve more compact and discriminative style features, named element-level features. Finally, we enhance our element-level style features by triplet embedding learning over crowdsourced triplets, which maps similar examples close to each other and dissimilar examples farther apart. The proposed algorithm can aggregate different local features into a global style feature representation and shows satisfactory discriminability. Our method can avoid the loss of style features from the 3D model to the views and can learn more discriminative style features by sparse learning. The experimental results show that our sparse style feature representation significantly improves the accuracy compared with recent state-of-the-art algorithms.