no code implementations • 23 May 2024 • Zuoyong Li, Qinghua Lin, Haoyi Fan, Tiesong Zhao, David Zhang
In this paper, we propose a new semi-supervised learning method called SIAVC for industrial accident video classification.
no code implementations • 9 Nov 2023 • Qinghua Lin, Zuoyong Li, Kun Zeng, Haoyi Fan, Wei Li, Xiaoguang Zhou
Considering the limited quantity of labeled video data, we propose a semi-supervised fire detection model called FireMatch, which is based on consistency regularization and adversarial distribution alignment.
no code implementations • 29 Jul 2023 • Zhongzheng Huang, Jiawei Wu, Tao Wang, Zuoyong Li, Anastasia Ioannou
Despite the success of deep neural networks in medical image classification, the problem remains challenging as data annotation is time-consuming, and the class distribution is imbalanced due to the relative scarcity of diseases.
Image Classification Semi-supervised Medical Image Classification
no code implementations • 24 Jul 2023 • Tao Wang, Zhongzheng Huang, Jiawei Wu, Yuanzheng Cai, Zuoyong Li
Medical image segmentation has made significant progress when a large amount of labeled data are available.
1 code implementation • 2 Jun 2023 • Jiawei Wu, Changqing Zhang, Zuoyong Li, Huazhu Fu, Xi Peng, Joey Tianyi Zhou
Cutting out an object and estimating its opacity mask, known as image matting, is a key task in image and video editing.
no code implementations • 19 Jan 2023 • Xiuen Wu, Tao Wang, Lingyu Liang, Zuoyong Li, Fum Yew Ching
The results indicate that our method with spatio-temporal context modeling is superior to existing methods for road obstacle detection.
1 code implementation • 1 Sep 2021 • Fengbin Zhang, Haoyi Fan, Ruidong Wang, Zuoyong Li, Tiancai Liang
In this paper, we propose an end-to-end model of Deep Dual Support Vector Data description based Autoencoder (Dual-SVDAE) for anomaly detection on attributed networks, which considers both the structure and attribute for attributed networks.
1 code implementation • 18 Feb 2020 • Haoyi Fan, Fengbin Zhang, Ruidong Wang, Liang Xi, Zuoyong Li
Unsupervised anomaly detection aims to identify anomalous samples from highly complex and unstructured data, which is pervasive in both fundamental research and industrial applications.
3 code implementations • 10 Feb 2020 • Haoyi Fan, Fengbin Zhang, Zuoyong Li
In this paper, we propose a deep joint representation learning framework for anomaly detection through a dual autoencoder (AnomalyDAE), which captures the complex interactions between network structure and node attribute for high-quality embeddings.
no code implementations • 10 Jun 2019 • Chun-Mei Feng, Yong Xu, Zuoyong Li, Jian Yang
It performs Sparse Representation Fusion based on the Diverse Subset of training samples (SRFDS), which reduces the impact of randomness of the sample set and enhances the robustness of classification results.
no code implementations • 11 May 2019 • Songsong Wu, Zhiqiang Lu, Hao Tang, Yan Yan, Songhao Zhu, Xiao-Yuan Jing, Zuoyong Li
Multi-view subspace clustering aims to divide a set of multisource data into several groups according to their underlying subspace structure.