Suzhen Lin

Suzhen Lin

Auto-generated profile, based on publicly available information

Suzhen Lin


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
2 September 2020 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
BWBin 中国 Wang
Bin 中国 Wang
HNHuifang Niu
Huifang Niu
JZJianchao Zeng
Jianchao Zeng
GBGuifeng Bai
Guifeng Bai
SLSuzhen Lin
Suzhen Lin
YWYanbo Wang
Yanbo Wang
The fusion of multi-band images including far-infrared image (FIRI), near-infrared image (NIRI) and visible image (VISI) primarily suffers from four challenges. One is the problem of simultaneous fusion for multiple images. Most existing methods are oriented towards the fusion of two objects, which is generally achieved with a sequential fusion method. This means that intermediate fusion results are repeatedly integrated with the unprocessed images until all images have been fused. However, this may amplify the blurring effect and even engender artifacts. Second, consistent training labels for image fusion cannot currently be obtained for some types of images (e.g., medical images and multi-band images), which may lead to the failed application of supervised learning methods. Third, the existing methods often do not directly focus on the potential mapping relationship between the original and resulting images, which usually increases the unpredictability of the fusion results. Fourth, redundant features or singularities are often not eliminated in the general fusion process, and both may interfere with or even obscure significant features in the source images. To address the abovementioned problems, this paper proposes a latent representation learning model that can synchronously integrate multi-band images without samples. Specifically, the model can capture the clean and distinctive features of the originals via latent low-rank and sparse embedding. The extracted intrinsic features are projected onto the target fusion space through an assumed mapping relationship. The final results were obtained through the designed optimization algorithm. In addition, numerous experiments were implemented to prove the rationality and feasibility of the proposed fusion model with subjective evaluation, objective indexes and convergence analysis.

12 January 2023 in IEEE Access
Verified
Journal Article
Open access
DYDong Yu
Dong Yu
SLSuzhen Lin
Suzhen Lin
XLXiaofei Lu
Xiaofei Lu
DLDawei Li
Dawei Li
YWYanbo Wang
Yanbo Wang
This study proposes a new deep neural network to solve the multi-band image synchronous fusion problem (MBF-Net). Unlike other deep learning-based methods, our network architecture design combines the ideas of model-driven and data-driven methods, so it is more interpretable. First, a new multi-band image synchronous fusion model is proposed. The source image in the data fidelity terms and the prior regularization are implicitly represented by the deep learning network and jointly learned from the training data. The proposed model is then solved using a half quadratic splitting (HQS) algorithm and unfolded into a deep fusion network. In addition, a new saliency loss function is proposed to retain thermal radiation information to enhance the fusion effect. Finally, the experimental results on the TNO dataset demonstrated the effectiveness of the proposed MBF-Net.

14 September 2026 in Electronics
Verified
Journal Article
Open access
PDF file
ZJZanxia Jin
Zanxia Jin
PQPinle Qin
Pinle Qin
JQJia Qin
Jia Qin
SZShuangjiao Zhai
Shuangjiao Zhai
SLSuzhen Lin
Suzhen Lin
JZJianchao Zeng
Jianchao Zeng
Text-based visual question answering (TextVQA) requires reasoning over images containing rich textual content, often involving knowledge beyond what is directly observable. Existing methods fuse visual objects and OCR tokens but struggle when questions require external knowledge. Moreover, naively incorporating retrieved knowledge often introduces irrelevant or misleading information, which may hinder reasoning rather than support it. To address these challenges, we propose a TextVQA framework that integrates external prior knowledge to support multimodal reasoning. Given an image and question, a task-aware knowledge retrieval module selects relevant candidates, which are then filtered and verified by a knowledge verification module leveraging large language models. The verified knowledge and question are compressed into compact embeddings via a perceiver-based semantic resampler and jointly processed with visual and OCR features in a multimodal reasoning module. Experiments on the TextVQA and ST-VQA datasets demonstrate that our approach effectively leverages external knowledge to improve performance on knowledge-intensive questions.

19 November 2026 in Sensors
Verified
Journal Article
Open access
PDF file
ZJZanxia Jin
Zanxia Jin
JAJialong An
Jialong An
SLSuzhen Lin
Suzhen Lin
Visible-infrared dual-band image captioning aims to generate accurate descriptions by exploiting complementary information from visible and infrared images. However, insufficient spatial relationship modeling and inflexible cross-modal fusion limit the effectiveness of existing methods. To address these issues, we propose a Transformer-based dual-band image captioning framework consisting of three key components. First, the Dual-band Multi-level Memory Encoder (DMME) integrates geometric and visual features to enhance spatial relationship modeling and employs learnable memory vectors for multi-level cross-modal alignment and feature fusion. Second, the Hierarchical Grid-Region Interaction (HGRI) module establishes hierarchical interactions between grid-level and region-level features, facilitating fine-grained cross-modal feature associations. Third, the Hierarchical Dynamic Fusion (HDF) decoder incorporates global visual constraints and an adaptive gating mechanism to dynamically balance the contributions of visible and infrared features across different scenes. Experiments on a visible-infrared image-captioning dataset demonstrate that our method achieves a CIDEr score of 122.9 ± 0.7, outperforming existing state-of-the-art methods.

27 May 2025 in arXiv
Verified
Preprint
Open access
PDF file
LMLinli Ma
Linli Ma
SLSuzhen Lin
Suzhen Lin
JZJianchao Zeng
Jianchao Zeng
ZJZanxia Jin
Zanxia Jin
YWYanbo Wang
Yanbo Wang
YLYubing Luo
Yubing Luo
Image fusion aims to combine complementary information from multiple source images to generate more comprehensive scene representations. Existing methods primarily rely on the stacking and design of network architectures to enhance the fusion performance, often ignoring the impact of dataset scene bias on model training. This oversight leads the model to learn spurious correlations between specific scenes and fusion weights under conventional likelihood estimation framework, thereby limiting fusion performance. To solve the above problems, this paper first re-examines the image fusion task from the causality perspective, and disentangles the model from the impact of bias by constructing a tailored causal graph to clarify the causalities among the variables in image fusion task. Then, the Back-door Adjustment based Feature Fusion Module (BAFFM) is proposed to eliminate confounder interference and enable the model to learn the true causal effect. Finally, Extensive experiments on three standard datasets prove that the proposed method significantly surpasses state-of-the-art methods in infrared and visible image fusion.

1 July 2016
Verified
Journal Article
Closed access
SSSu-Zhen Lin Su-zhen
Su-Zhen Lin Su-zhen
DDDong-Juan Wang Dong-juan
Dong-Juan Wang Dong-juan
XXXiao-Xia Wang Xiao-xia
Xiao-Xia Wang Xiao-xia
XXXiao-Hong Zhu Xiao-hong
Xiao-Hong Zhu Xiao-hong