no code implementations • 8 Apr 2024 • Jingxin Wang, Renxiang Guan, Kainan Gao, Zihao Li, Hao Li, Xianju Li, Chang Tang
Multi-level graph subspace contrastive learning: multi-level contrastive learning was conducted to obtain local-global joint graph representations, to improve the consistency of the positive samples between views, and to obtain more robust graph embeddings.
no code implementations • 15 Dec 2023 • Renxiang Guan, Zihao Li, Xianju Li, Chang Tang
The pixel-level contrastive learning method can effectively improve the ability of the model to capture fine features of HSI but requires a large time overhead.
no code implementations • 11 Dec 2023 • Renxiang Guan, Zihao Li, Xianju Li, Chang Tang, Ruyi Feng
In this study, contrastive multi-view subspace clustering of HSI was proposed based on graph convolutional networks.
1 code implementation • 16 Nov 2023 • Zhenglai Li, Chang Tang, Xinwang Liu, Changdong Li, Xianju Li, Wei zhang
How to capture the semantic variations associated with the changed and unchanged regions from the patch-level annotations to obtain promising change results is the critical challenge for the weakly supervised change detection task.
no code implementations • 26 Aug 2023 • Jian Zhu, Wen Cheng, Yu Cui, Chang Tang, Yuyang Dai, Yong Li, Lingfang Zeng
Hash representation learning of multi-view heterogeneous data is the key to improving the accuracy of multimedia retrieval.
no code implementations • 23 Jul 2023 • Qingren Yao, Yuan Zhou, Chang Tang, Wei Xiang
For hyperspectral image change detection (HSI-CD), one key challenge is to reduce band redundancy, as only a few bands are crucial for change detection while other bands may be adverse to it.
1 code implementation • 14 Jun 2023 • Xiao He, Chang Tang, Xinwang Liu, Wei zhang, Kun Sun, Jiangfeng Xu
S2ADet comprises a hyperspectral information decoupling (HID) module, a two-stream feature extraction network, and a one-stage detection head.
1 code implementation • 31 May 2023 • Zhenglai Li, Chang Tang, Xianju Li, Weiying Xie, Kun Sun, Xinzhong Zhu
Specifically, an online uncertainty estimation branch is constructed to model the pixel-wise uncertainty, which is supervised by the difference between predicted change maps and corresponding ground truth during the training process.
1 code implementation • CVPR 2023 • Weiqing Yan, Yuanyang Zhang, Chenlei Lv, Chang Tang, Guanghui Yue, Liang Liao, Weisi Lin
However, most existing deep clustering methods learn consensus representation or view-specific representations from multiple views via view-wise aggregation way, where they ignore structure relationship of all samples.
3 code implementations • IEEE Transactions on Image Processing 2022 • Zhenglai Li, Chang Tang, Xiao Zheng, Xinwang Liu, Senior Member, Wei zhang, Member, IEEE, and En Zhu
Specifically, multiple affinity matrices constructed from the incomplete multi-view data are treated as a thirdorder low rank tensor with a tensor factorization regularization which preserves the high-order view correlation and sample correlation.
1 code implementation • IEEE International Conference on Multimedia and Expo 2021 • Zhenglai Li, Chang Tang, Xinwang Liu, Xiao Zheng, Wei zhang, En Zhu
In this paper, we propose a novel incomplete multi-view clustering method, in which a tensor nuclear norm regularizer elegantly diffuses the information of multi-view block-diagonal structure across different views.
1 code implementation • IEEE Transactions on Multimedia 2021 • Zhenglai Li, Chang Tang, Xinwang Liu, Xiao Zheng, Guanghui Yue, Wei zhang
Furthermore, we unify the spectral embedding and low rank tensor learning into a unified optimization framework to determine the spectral embedding matrices and tensor representation jointly.
1 code implementation • International Joint Conferences on Artificial Intelligence Organization 2021 • Chang Tang, Xinwang Liu, En Zhu, Lizhe Wang, Albert Zomaya
In this paper, we propose a hyperspectral band selection method via spatial-spectral weighted region-wise multiple graph fusion-based spectral clustering, referred to as RMGF briefly.
1 code implementation • ICCV 2021 • Xinwang Liu, Sihang Zhou, Li Liu, Chang Tang, Siwei Wang, Jiyuan Liu, Yi Zhang
After that, we theoretically show that the objective of SimpleMKKM is a special case of this local kernel alignment criterion with normalizing each base kernel matrix.
no code implementations • 26 May 2020 • Jing Zhang, Wanqing Li, Lu Sheng, Chang Tang, Philip Ogunbona
Given an existing system learned from previous source domains, it is desirable to adapt the system to new domains without accessing and forgetting all the previous domains in some applications.
no code implementations • 4 Aug 2019 • Yawei Zhao, En Zhu, Xinwang Liu, Chang Tang, Deke Guo, Jianping Yin
Specifically, we propose a new variant of the alternating direction method of multipliers (ADMM) to solve this problem efficiently.
no code implementations • CVPR 2019 • Chang Tang, Xinzhong Zhu, Xinwang Liu, Lizhe Wang, Albert Zomaya
After that, the fused shallow features are propagated to top layers for refining the fine details of detected defocus blur regions, and the fused semantic features are propagated to bottom layers to assist in better locating the defocus regions.
Ranked #1 on Defocus Estimation on CUHK - Blur Detection Dataset (F-measure metric)
no code implementations • 17 Mar 2018 • Pichao Wang, Wanqing Li, Zhimin Gao, Chang Tang, Philip Ogunbona
This paper proposes three simple, compact yet effective representations of depth sequences, referred to respectively as Dynamic Depth Images (DDI), Dynamic Depth Normal Images (DDNI) and Dynamic Depth Motion Normal Images (DDMNI), for both isolated and continuous action recognition.
no code implementations • CVPR 2017 • Pichao Wang, Wanqing Li, Zhimin Gao, Yuyao Zhang, Chang Tang, Philip Ogunbona
Based on the scene flow vectors, we propose a new representation, namely, Scene Flow to Action Map (SFAM), that describes several long term spatio-temporal dynamics for action recognition.
Ranked #3 on Hand Gesture Recognition on ChaLearn val
no code implementations • 7 Jan 2017 • Pichao Wang, Wanqing Li, Song Liu, Zhimin Gao, Chang Tang, Philip Ogunbona
This paper proposes three simple, compact yet effective representations of depth sequences, referred to respectively as Dynamic Depth Images (DDI), Dynamic Depth Normal Images (DDNI) and Dynamic Depth Motion Normal Images (DDMNI).
Ranked #2 on Hand Gesture Recognition on ChaLearn val
no code implementations • 21 Jan 2016 • Jing Zhang, Wanqing Li, Philip O. Ogunbona, Pichao Wang, Chang Tang
Human action recognition from RGB-D (Red, Green, Blue and Depth) data has attracted increasing attention since the first work reported in 2010.
no code implementations • ICCV 2015 • Lei Wang, Jianjia Zhang, Luping Zhou, Chang Tang, Wanqing Li
It proposes an open framework to use the kernel matrix over feature dimensions as a generic representation and discusses its properties and advantages.
no code implementations • 10 Nov 2015 • Chang Tang, Pichao Wang, Wanqing Li
This paper presents a fast yet effective method to recognize actions from stream of noisy skeleton data, and a novel weighted covariance descriptor is adopted to accumulate evidence.
no code implementations • IEEE Transactions on Human-Machine Systems 2016 2015 • Pichao Wang, Wanqing Li, Zhimin Gao, Jing Zhang, Chang Tang, Philip Ogunbona
In addition, the method was evaluated on the large dataset constructed from the above datasets.
Ranked #9 on Multimodal Activity Recognition on EV-Action
no code implementations • 20 Jan 2015 • Pichao Wang, Wanqing Li, Zhimin Gao, Jing Zhang, Chang Tang, Philip Ogunbona
The results show that our approach can achieve state-of-the-art results on the individual datasets and without dramatical performance degradation on the Combined Dataset.