All Outputs (4)

A Secure User Anonymity-Preserving Biometrics and PUFs-Based Multi-Server Authentication Scheme With Key Agreement in 5G Networks (2024)
Journal Article
Xu, D., Bian, W., Li, Q., Xie, D., Zhao, J., & Hu, Y. (online). A Secure User Anonymity-Preserving Biometrics and PUFs-Based Multi-Server Authentication Scheme With Key Agreement in 5G Networks. IEEE internet of things journal, https://doi.org/10.1109/JIOT.2024.3486005

The 5G networks can provide high data rates, ultra-low latency and huge network capacity. In 5G networks environment, the popularity of the Internet of Things (IoT) has led to a rapid increase in the amount of data. Multi-server distributed cloud com... Read More about A Secure User Anonymity-Preserving Biometrics and PUFs-Based Multi-Server Authentication Scheme With Key Agreement in 5G Networks.

ScribFormer: Transformer Makes CNN Work Better for Scribble-based Medical Image Segmentation (2024)
Journal Article
Li, Z., Zheng, Y., Shan, D., Yang, S., Li, Q., Wang, B., …Shen, D. (2024). ScribFormer: Transformer Makes CNN Work Better for Scribble-based Medical Image Segmentation. IEEE Transactions on Medical Imaging, 43(6), 2254-2265. https://doi.org/10.1109/TMI.2024.3363190

Most recent scribble-supervised segmentation methods commonly adopt a CNN framework with an encoder-decoder architecture. Despite its multiple benefits, this framework generally can only capture small-range feature dependency for the convolutional la... Read More about ScribFormer: Transformer Makes CNN Work Better for Scribble-based Medical Image Segmentation.

Using outlier elimination to assess learning-based correspondence matching methods (2024)
Journal Article
Ding, X., Luo, Y., Jie, B., Li, Q., & Cheng, Y. (2024). Using outlier elimination to assess learning-based correspondence matching methods. Information Sciences, 659, Article 120056. https://doi.org/10.1016/j.ins.2023.120056

Recently, deep learning (DL) technology has been widely used in correspondence matching. The learning-based models are usually trained on benign image pairs with partial overlaps. Since DL model is usually data-dependent, non-overlapping images may b... Read More about Using outlier elimination to assess learning-based correspondence matching methods.

NeuFG: Neural Fuzzy Geometric Representation for 3D Reconstruction (2024)
Journal Article
Hong, Q., Yang, C., Chen, J., Li, Z., Wu, Q., Li, Q., & Tian, J. (2024). NeuFG: Neural Fuzzy Geometric Representation for 3D Reconstruction. IEEE Transactions on Fuzzy Systems, https://doi.org/10.1109/TFUZZ.2024.3447088

3D reconstruction from multi-view images is considered as a longstanding problem in computer vision and graphics. In order to achieve high-fidelity geometry and appearance of 3D scenes, this paper proposes a novel geometric object learning method for... Read More about NeuFG: Neural Fuzzy Geometric Representation for 3D Reconstruction.