Taotao Lai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Taotao Lai has a total of 87 co-authors. Here are the top co-authors by number of shared publications:
- Zuoyong Li
Minjiang University
14 shared publications - Hanzi Wang
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China
6 shared publications - Yizhang Liu
College of Computer and Data Science, Fuzhou University, Fuzhou, China
6 shared publications Riqing Chen
5 shared publications- Shuyuan Lin
College of Cyber Security, Jinan University, Guangzhou, China
5 shared publications - Hamido Fujita
Malaysia-Japan International Institute of Technology, University Teknologi Malaysia, Kuala Lumpur, Malaysia
4 shared publications
Latest Publications
- 25 October 2026
- Published by Elsevier in Pattern Recognition
- Vol. 183
Graph Transformer with Patchwise Comparisons for two-view correspondence pruning
- 25 October 2026
- Published by Elsevier in Pattern Recognition
- Vol. 183
Graph Transformer with Patchwise Comparisons for two-view correspondence pruning
- 2 September 2026
- Published by Springer Nature
- p. 285-295
Channel-Aware Motion Field Consensus for Two-View Correspondence Learning
- 2 September 2026
- Published by Springer Nature
- p. 285-295
Channel-Aware Motion Field Consensus for Two-View Correspondence Learning
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-14
A Channel-Region Adaptive Unet for Lung Inflammation Segmentation
Accurate lung inflammation segmentation is essential for clinical decision-making, yet remains challenging due to the large variability in lesion appearance and location across different lung regions. Existing CNN-based models excel at local feature extraction, but they struggle to capture long-range dependencies and complex spatial relationships, such as those between the left and right lung lobes. Transformer-based models, while effective in modeling long-range dependencies, incur high computational costs and often fail to capture irregular anatomical relationships due to their reliance on Euclidean positional encodings. To overcome these challenges, we propose a novel Channel-Region Adaptive Unet (CRA-Unet) for accurate lung inflammation segmentation. Specifically, we design a Channel-Region Adaptive (CRA) layer that expands the recalibration process of the Squeeze-Excitation layer to include not only the channel dimension but also the height and width dimensions, enabling dynamical element-wise feature adjustment within different regions of interest across all three dimensions—channel, height, and width. Additionally, we propose a region-adaptive positional encoding strategy that learns dynamic weights for spatial locations, allowing the model to capture both intra-region and inter-region spatial relationships. Unlike traditional Euclidean positional encodings, which assume regular and grid-like spatial structures, our strategy can adapt to the irregular and asymmetric spatial relationships commonly found in anatomical structures such as the lungs. Experimental results on several datasets demonstrate that our CRA-Unet achieves state-of-the-art segmentation performance while maintaining high computational efficiency.
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-14
A Channel-Region Adaptive Unet for Lung Inflammation Segmentation
Accurate lung inflammation segmentation is essential for clinical decision-making, yet remains challenging due to the large variability in lesion appearance and location across different lung regions. Existing CNN-based models excel at local feature extraction, but they struggle to capture long-range dependencies and complex spatial relationships, such as those between the left and right lung lobes. Transformer-based models, while effective in modeling long-range dependencies, incur high computational costs and often fail to capture irregular anatomical relationships due to their reliance on Euclidean positional encodings. To overcome these challenges, we propose a novel Channel-Region Adaptive Unet (CRA-Unet) for accurate lung inflammation segmentation. Specifically, we design a Channel-Region Adaptive (CRA) layer that expands the recalibration process of the Squeeze-Excitation layer to include not only the channel dimension but also the height and width dimensions, enabling dynamical element-wise feature adjustment within different regions of interest across all three dimensions—channel, height, and width. Additionally, we propose a region-adaptive positional encoding strategy that learns dynamic weights for spatial locations, allowing the model to capture both intra-region and inter-region spatial relationships. Unlike traditional Euclidean positional encodings, which assume regular and grid-like spatial structures, our strategy can adapt to the irregular and asymmetric spatial relationships commonly found in anatomical structures such as the lungs. Experimental results on several datasets demonstrate that our CRA-Unet achieves state-of-the-art segmentation performance while maintaining high computational efficiency.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (10) , 1
Deterministic Model Fitting via Neighborhood Information and Greedy Search
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (10) , 1
Deterministic Model Fitting via Neighborhood Information and Greedy Search
- 12 November 2025
- Published by Springer Nature
- p. 215-225
Guilded Outlier Removal Via Convolution Self-Attention Fusion
- 12 November 2025
- Published by Springer Nature
- p. 215-225
Guilded Outlier Removal Via Convolution Self-Attention Fusion
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8577-8585
Two-View Correspondence Pruning via Channel-Spatial Interaction and Bidirectional Consensus Interaction
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8577-8585
Open AccessTwo-View Correspondence Pruning via Channel-Spatial Interaction and Bidirectional Consensus Interaction
- 2 March 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 173
A unified transductive and inductive learning framework for Few-Shot Learning using Graph Neural Networks
- 2 March 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 173
A unified transductive and inductive learning framework for Few-Shot Learning using Graph Neural Networks
- 9 January 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 310
PRNet: Parallel Reinforcement Network for two-view correspondence learning
- 9 January 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 310
PRNet: Parallel Reinforcement Network for two-view correspondence learning
- 13 September 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 260
Leukocyte classification using relative-relationship-guided contrastive learning
- 13 September 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 260
Leukocyte classification using relative-relationship-guided contrastive learning