Zonglin Liu

Zonglin Liu

Auto-generated profile, based on publicly available information

Zonglin Liu

School of Science, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
7 November 2025 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
HWHanzhang Wang
Hanzhang Wang
ZLZonglin Liu
Zonglin Liu
ZZZhiwei Zhong
Zhiwei Zhong
QSQiangqiang Shen
Qiangqiang Shen
YLYongsheng Liang
Yongsheng Liang
YCYongyong Chen
Yongyong Chen
Multi-view clustering (MVC) has emerged as a powerful approach for integrating diverse sources of information from complex datasets. Nevertheless, existing methods struggle to accurately capture the global correlations and high-order structures in the data, and employ anchor-based techniques within a single dimension, limiting their representation. To address these issues, we propose an Anchor-induced Serial Tensor Representation (ASTR) framework, which effectively harnesses serial tensor representation to capture comprehensive multi-view information while reducing approximation errors and enhancing clustering performance. Specifically, ASTR begins with projection learning to explore low-dimensional latent spaces in multi-view data. Then, we introduce multi-anchor learning, where multiple anchor configurations are generated within the latent spaces, yielding a set of corresponding bipartite graphs. Besides, we organize these bipartite graphs into a sequence of global tensors, forming the serial tensor representation that encapsulates high-order inter- and intra-view relationships. Furthermore, we introduce the Laplace function to achieve a more accurate tensor rank approximation, complemented by a thorough theoretical analysis. Finally, a one-step clustering process, guided by adaptive weights, directly fuses the learned graphs to produce the final clustering indicator matrix. Experimental results demonstrate that ASTR possesses superior clustering accuracy and comparable efficiency.

21 May 2026 in IEEE Transactions on Artificial Intelligence
Verified
Journal Article
Closed access
QSQiangqiang Shen
Qiangqiang Shen
ZLZonglin Liu
Zonglin Liu
HWHanzhang Wang
Hanzhang Wang
YLYongsheng Liang
Yongsheng Liang
YCYongyong Chen
Yongyong Chen
SWShiqi Wang
Shiqi Wang
To balance deep learning performance and interpretability, convolutional sparse coding (CSC) has successfully incorporated differentiable optimization layers in place of the standard convolutional layers of traditional deep neural networks (DNN). However, CSC models prefer to fall into local sparsity under the ℓ1-norm, whose optimization shows limitations in preserving the geometric structure and global sparsity of tensor data. In this paper, we propose a Linearized Tensor Low-Rank Convolutional Network (LTLRCNet) to refresh the differentiable optimization layers for DNN (e.g., ResNet and UNet), which instead optimizes the tensor low-rank minimization problem for global sparsity without ruining the intrinsic structure of data. Specifically, instead of simply replacing the ℓ1-norm with a tensor low-rank regularizer, we first propose a linearized tensor lowrank representation (LTLRR) model optimized by a linearized alternating direction method to decouple the dictionary and code coefficient without introducing an auxiliary variable, whose convergence is proved theoretically. Subsequently, we extend the LTLRR model into a deep unfolding network, such as the LTLRCNet, by engineering a convolutional dictionary that functions as a differentiable optimization layer, effectively substituting the conventional convolutional layer. To match the deep unfolding framework and avoid the gradient explosion, we apply a rank-one tactic bearing the Frank-Wolfe algorithm to solve the tensor low-rank minimization problem instead of conducting the cumbersome full-rank tensor singular value decomposition. Experimental results on image classification and segmentation show the potential of our LTLRCNet with its modeling-based layers to maintain significant performance and interpretability.