Xin Zhong

Dr. Xin Zhong

Department of Computer Science, College of Information Science & Technology, University of Nebraska at Omaha, Omaha, NE 68182, USA
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
3 July 2020 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
XZXin Zhong
Xin Zhong
Pei-Chi HuangPei-Chi Huang
Pei-Chi Huang
SMSpyridon Mastorakis
Spyridon Mastorakis
FSFrank Y. Shih
Frank Y. Shih
Digital image watermarking is the process of embedding and extracting a watermark covertly on a cover-image. To dynamically adapt image watermarking algorithms, deep learning—based image watermarking schemes have attracted increased attention during recent years. However, existing deep learning—based watermarking methods neither fully apply the fitting ability to learn and automate the embedding and extracting algorithms, nor achieve the properties of robustness and blindness simultaneously. In this paper, a robust and blind image watermarking scheme based on deep learning neural networks is proposed. To minimize the requirement of domain knowledge, the fitting ability of deep neural networks is exploited to learn and generalize an automated image watermarking algorithm. A deep learning architecture is specially designed for image watermarking tasks, which will be trained in an unsupervised manner to avoid human intervention and annotation. To facilitate flexible applications, the robustness of the proposed scheme is achieved without requiring any prior knowledge or adversarial examples of possible attacks. A challenging case of watermark extraction from phone camera—captured images demonstrates the robustness and practicality of the proposal. The experiments, evaluation, and application cases confirm the superiority of the proposed scheme.

30 October 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
XZXin Zhong
Xin Zhong
ADArjon Das
Arjon Das
FAFahad Alrasheedi
Fahad Alrasheedi
ATAbdullah All NA Tanvir
Abdullah All NA Tanvir
This paper presents a comprehensive survey of deep learning-based image watermarking; this technique entails the invisible embedding and extraction of watermarks within a cover image, aiming for a seamless combination of robustness and adaptability. We navigate the complex landscape of this interdisciplinary domain, linking historical foundations, current innovations, and prospective developments. Unlike existing literature, our study concentrates exclusively on image watermarking with deep learning, delivering an in-depth, yet brief analysis enriched by three fundamental contributions. First, we introduce a refined categorization, segmenting the field into embedder–extractor, deep networks for feature transformation, and hybrid methods. This taxonomy, inspired by the varied roles of deep learning across studies, is designed to infuse clarity, offering readers technical insights and directional guidance. Second, our exploration dives into representative methodologies, encapsulating the diverse research directions and inherent challenges within each category to provide a consolidated perspective. Lastly, we venture beyond established boundaries, outlining emerging frontiers and providing detailed insights into prospective research avenues.

13 March 2024 in IEEE Access
Verified
Journal Article
Open access
TMTravis Munyer
Travis Munyer
ATAbdullah All NA Tanvir
Abdullah All NA Tanvir
ADArjon Das
Arjon Das
XZXin Zhong
Xin Zhong
The rapid advancement of Large Language Models (LLMs) has significantly enhanced the capabilities of text generators.With the potential for misuse escalating, the importance of discerning whether texts are human-authored or generated by LLMs has become paramount. Several preceding studies have ventured to address this challenge by employing binary classifiers to differentiate between human-written and LLM-generated text. Nevertheless, the reliability of these classifiers has been subject to question. Given that consequential decisions may hinge on the outcome of such classification, it is imperative that text source detection is of high caliber. In light of this, the present paper introduces DeepTextMark, a deep learning-driven text watermarking methodology devised for text source identification. By leveraging Word2Vec and Sentence Encoding for watermark insertion, alongside a transformer-based classifier for watermark detection, DeepTextMark epitomizes a blend of blindness, robustness, imperceptibility, and reliability. As elaborated within the paper, these attributes are crucial for universal text source detection, with a particular emphasis in this paper on text produced by LLMs. DeepTextMark offers a viable "add-on" solution to prevailing text generation frameworks, requiring no direct access or alterations to the underlying text generation mechanism. Experimental evaluations underscore the high imperceptibility, elevated detection accuracy, augmented robustness, reliability, and swift execution of DeepTextMark.

19 January 2023 in IEEE Access
Verified
Journal Article
Open access
FAFahad Alrasheedi
Fahad Alrasheedi
XZXin Zhong
Xin Zhong
Pei-Chi HuangPei-Chi Huang
Pei-Chi Huang
During the last decades, many studies have been dedicated to improving the performance of neural networks, for example, the network architectures, initialization, and activation. However, investigating the importance and effects of learnable padding methods in deep learning remains relatively open. To mitigate the gap, this paper proposes a novel trainable Padding Module that can be placed in a deep learning model. The Padding Module can optimize itself without requiring or influencing the model’s entire loss function. To train itself, the Padding Module constructs a ground truth and a predictor from the inputs by leveraging the underlying structure in the input data for supervision. As a result, the Padding Module can learn automatically to pad pixels to the border of its input images or feature maps. The padding contents are realistic extensions to its input data and simultaneously facilitate the deep learning model’s downstream task. Experiments have shown that the proposed Padding Module outperforms the state-of-the-art competitors and the baseline methods. For example, the Padding Module has 1.23% and 0.44% more classification accuracy than the zero padding when tested on the VGG16 and ResNet50.

10 March 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
XZXin Zhong
Xin Zhong
GLGehao Lu
Gehao Lu
HLHao Li
Hao Li
Deep learning-based medical image segmentation methods are generally divided into convolutional neural networks (CNNs) and Transformer-based models. Traditional CNNs are limited by their receptive field, making it challenging to capture long-range dependencies. While Transformers excel at modeling global information, their high computational complexity restricts their practical application in clinical scenarios. To address these limitations, this study introduces VMAXL-UNet, a novel segmentation network that integrates Structured State Space Models (SSM) and lightweight LSTMs (xLSTM). The network incorporates Visual State Space (VSS) and ViL modules in the encoder to efficiently fuse local boundary details with global semantic context. The VSS module leverages SSM to capture long-range dependencies and extract critical features from distant regions. Meanwhile, the ViL module employs a gating mechanism to enhance the integration of local and global features, thereby improving segmentation accuracy and robustness. Experiments on datasets such as ISIC17, ISIC18, CVC-ClinicDB, and Kvasir demonstrate that VMAXL-UNet significantly outperforms traditional CNNs and Transformer-based models in capturing lesion boundaries and their distant correlations. These results highlight the model’s superior performance and provide a promising approach for efficient segmentation in complex medical imaging scenarios.

1 January 2024 in Journal of Ophthalmology
Verified
Journal Article
Open access
XZXin Zhong
Xin Zhong
YLYan Li
Yan Li
YLYuancun Li
Yuancun Li
GWGeng Wang
Geng Wang
YDYali Du
Yali Du
MZMingzhi Zhang
Mingzhi Zhang
Background. This study aims to investigate the agreement between the NK and KS formulas in predicting the vault after implantation of an EVO‐implantable collamer lens (ICL). Methods. This retrospective study included 106 eyes of 57 patients who underwent ICL‐V4c implantation. Preoperative vault prediction was conducted by utilizing the NK and KS formulas, with postoperative measurements by anterior segment optical coherence tomography (AS‐OCT) at one month. The analysis focused on the consistency between predicted and achieved vaults, as well as the correlation between the achieved vault and various biometric parameters. Results. The mean achieved vault was 605.25 ± 212.72 µm, which was significantly smaller than the predicted vaults of 710.08 ± 195.08 and 673.80 ± 212.76 µm, using the NK and KS formulas, respectively (P < 0.05). The mean differences between the achieved vault and the predicted vault using the NK formula and KS formula were −104.82 μm (95% LoA: −600.38–391.19 μm) and −68.55 μm (95% LoA: −628.91–491.82 μm), respectively. Anterior chamber depth (ACD), vertical sulcus‐to‐sulcus (V‐STS) diameter, and crystalline lens rise (CLR) were independent factors associated with the achieved vault (P < 0.05). The two formulas showed no statistically significant difference in absolute prediction error (APE). Conclusion. The NK formula exhibited superior consistency and low predictive error compared to the KS formula in the 12.6 mm ICL group. AS‐OCT measurements overestimated the predicted ICL vault, especially in the 13.2 mm ICL size selection. Relying solely on the NK or KS formulas for predicting vaults before ICL surgery is not recommended.