Selected Papers with Code

Machine Vision

This section mainly focuses on machine vision topics such as image segmentation, object detection, etc.

Graph Data Analysis

This section mainly focuses on graph data analysis, such as social network analysis, community detection, core-periphery detection, link prediction, etc.

Machine Vision

Yao, B., Zhang, D., Zhao, J., Zheng, Y., Peng, C.* “Active Learning with Joint Probabilistic Modeling for Point Cloud Semantic Segmentation.” Knowledge-Based Systems (2025): 114171. [code]
Zewei Wu, Chengbin Peng*. “Few-shot image classification for defect detection in aviation materials.” Measurement (2025): 117749.
Pengcheng Xiang, Baochen Yao, Zefeng Jiang, Chengbin Peng*. “Self-Enhanced Feature Fusion for RGB-D Semantic Segmentation.” IEEE Signal Processing Letters (2024). [code]
Dongjie Zhang, Yuting Hong, Xiaojie Qiu, Li Dong, Diqun Yan, Chengbin Peng*. “C2F2: Cross-Task Cross-Domain Feature Fusion for Semi-Supervised Change Detection.” IEEE Geoscience and Remote Sensing Letters (2024). [code]
- It improves the semi-supervised learning by introducing models for other tasks or domains.
Yuting Hong, Li Dong, Xiaojie Qiu, Hui Xiao, Baochen Yao, Siming Zheng, and Chengbin Peng*. “A multi-view consistency framework with semi-supervised domain adaptation.” Engineering Applications of Artificial Intelligence 136 (2024): 108886. [code]
- It enhances classification in a partially labeled target domain with a fully labeled source domain by introducing a multi-view consistency framework with debiasing strategies and cross-domain affinity learning
Zefeng Jiang, Baochen Yao, Kangkang Song, Xiaojie Qiu, and Chengbin Peng*. “Point Cloud Semantic Segmentation by Adaptively Fusing Information With Varying Distances.” IEEE Signal Processing Letters (2024). [code]
- It proposes a graph-based approach by fusing information with adaptive distances to improve point cloud segmentation.
Baochen Yao, Li Dong, Xiaojie Qiu, Kangkang Song, Diqun Yan, and Chengbin Peng*. “Uncertainty-guided Contrastive Learning for Weakly Supervised Point Cloud Segmentation.” IEEE Transactions on Geoscience and Remote Sensing (2024). [code]
- It proposes an uncertainty metric based on prototype entropy to estimate the reliability of model predictions on different points, and a negative contrastive learning using this metric demonstrates its effectiveness.
Ruiyun Chen, Guitao Yu, Zhen Qin, Kangkang Song, Jianfei Tu, Xianliang Jiang, Dan Liang, and Chengbin Peng*. “Patch Matching for Few-shot Industrial Defect Detection.” IEEE Transactions on Instrumentation and Measurement (2024). [code]
- It proposes to use patch matching and adaptive feature banks to improve the pixel-level and image-level defect detection.
Xiao, Hui, Yuting Hong, Li Dong, Diqun Yan, Junjie Xiong, Jiayan Zhuang, Dongtai Liang, and Chengbin Peng*. “Multi-Level Label Correction by Distilling Proximate Patterns for Semi-supervised Semantic Segmentation.” IEEE Transactions on Multimedia (2024). [code]
- It utilizes graph learning to improve the semi-supervised learning.
Yao, Baochen, Hui Xiao, Jiayan Zhuang, and Chengbin Peng*. “Weakly Supervised Learning for Point Cloud Semantic Segmentation with Dual Teacher.” IEEE Robotics and Automation Letters (2023). [code]
Hao, Huazheng, Hui Xiao, Li Dong, Diqun Yan, Dongtai Liang, Jiayan Zhuang, and Chengbin Peng*. “A Pseudo-Dual Self-Rectification Framework for Semantic Segmentation.” In 2023 IEEE International Conference on Multimedia and Expo (ICME), pp. 408-413. IEEE, 2023. [code]
- It aims to improve the efficiency of semi-supervised learning by reducing the model size.
Yi Zhu, Jiayan Zhuang, Sichao Ye, Ningyuan Xu, Jiangjian Xiao, Jianfeng Gu, Yiwu Fang, Chengbin Peng, and Ying Zhu. “Domain generalization in nematode classification.” Computers and Electronics in Agriculture 207 (2023): 107710.
Hao Xu, Hui Xiao, Huazheng Hao, Li Dong, Xiaojie Qiu, and Chengbin Peng. “Semi-supervised learning with pseudo-negative labels for image classification.” Knowledge-Based Systems 260 (2023): 110166. [code]
- It proposes to improve the performance of SSL with pseudo-negative labels.
Hui Xiao, Li Dong, Hao Xu, Shuibo Fu, Yan Diqun, Kangkang Song, and Chengbin Peng. “Semi-supervised semantic segmentation with cross teacher training.” Neurocomputing 508 (2022): 36-46. [code]
- It proposes to improve the performance of SSL with multiple pairs of student-teacher submodels using cross teaching, to avoid submodel coupling.
Zheming Fan, Chengbin Peng, Licun Dai, Feng Cao, Jianyu Qi, and Wenyi Hua. “A deep learning-based ensemble method for helmet-wearing detection.” PeerJ Computer Science 6 (2020): e311. [code]
Chengbin Peng, Wei Bu, Jiangjian Xiao, Ka-chun Wong, and Minmin Yang. “An improved neural network cascade for face detection in large scene surveillance.” Applied Sciences 8, no. 11 (2018): 2222.
Wei Bu, Jiangjian Xiao, Chuanhong Zhou, Minmin Yang, and Chengbin Peng*. “A cascade framework for masked face detection.” In 2017 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM), pp. 458-462. IEEE, 2017.

Graph Data Analysis

Y Zhang, X Shen, Y Xie, KC Wong, W Xie, C Peng. “Directed Link Prediction using GNN with Local and Global Feature Fusion.” IEEE Transactions on Network Science and Engineering (2024). [code]
Yang, Lintao, Pietro Liò, Xu Shen, Yuyang Zhang, and Chengbin Peng. “Adaptive multi-scale Graph Neural Architecture Search framework.” Neurocomputing (2024): 128094. [code]
- It is able to optimize graph neural network architectures by searching for message-passing and feature fusion strategies simultaneously, to combine neighboring nodes with different distances in different ways.
Xu Shen, Pietro Lio, Lintao Yang, Ru Yuan, Yuyang Zhang, and Chengbin Peng. “Graph Rewiring and Preprocessing for Graph Neural Networks Based on Effective Resistance.” IEEE Transactions on Knowledge and Data Engineering (2024). [code]
- It proposes a framework to simultaneously address the issues of over-smoothing and over-squashing in GNNs.
Wang, Zhonghao, Ru Yuan, Jiaye Fu, Ka-Chun Wong, and Chengbin Peng. “Core–Periphery Detection Based on Masked Bayesian Nonnegative Matrix Factorization.” IEEE Transactions on Computational Social Systems (2024). [code]
- It proposes an NMF-based approach for core-periphery detection.
Xu Shen, Yuyang Zhang, Yu Xie, Ka-Chun Wong, and Chengbin Peng. “A Block-Based Adaptive Decoupling Framework for Graph Neural Networks.” Entropy 24, no. 9 (2022): 1190. [code]
- It proposes a framework to tackle the over-smoothing issues for deep graph neural networks.
Xin Shen, Sarah Aliko, Yue Han, Jeremy I. Skipper, and Chengbin Peng. “Finding core-periphery structures with node influences.” IEEE Transactions on Network Science and Engineering 9, no. 2 (2021): 875-887. [code]
- It proposes a novel core–periphery detection algorithm that also works for brain activity data.
Xin Shen, Yue Han, Wenqian Li, Ka-Chun Wong, and Chengbin Peng. “Finding core-periphery structures in large networks.” Physica A: Statistical Mechanics and its Applications 581 (2021): 126224. [code]
- It proposes core–periphery (CP) score to evaluate the quality of CP algorithms.
Peng, Chengbin, Zhihua Zhang, Ka-Chun Wong, Xiangliang Zhang, and David Keyes. “A scalable community detection algorithm for large graphs using stochastic block models.” In Twenty-Fourth International Joint Conference on Artificial Intelligence. 2015. [code]
- It proposes a parallel algorithm for SBM models.
Peng, Chengbin, Tamara G. Kolda, and Ali Pinar. “Accelerating community detection by using k-core subgraphs.” arXiv preprint arXiv:1403.2226 (2014).
Peng, Chengbin, Xiaogang Jin, and Meixia Shi. “Epidemic threshold and immunization on generalized networks.” Physica A: Statistical Mechanics and its Applications 389, no. 3 (2010): 549-560.

Machine Vision

Graph Data Analysis

Other Topics

Machine Vision

Graph Data Analysis

Other Topics