4 code implementations • 22 Aug 2017 • Yu Zhao, Rennong Yang, Guillaume Chevalier, Maoguo Gong
Human activity recognition (HAR) has become a popular topic in research because of its wide application.
no code implementations • 9 Dec 2017 • Dayong Tian, Maoguo Gong, Deyun Zhou, Jiao Shi, Yu Lei
As unsupervised multimodal hashing methods are usually inferior to supervised ones, while the supervised ones requires too much manually labeled data, the proposed method in this paper utilizes a part of labels to design a semi-supervised multimodal hashing method.
no code implementations • 8 Apr 2019 • Jia Liu, Maoguo Gong, Haibo He
In this paper, we propose a nucleus neural network (NNN) and corresponding connecting architecture learning method.
1 code implementation • 12 Oct 2020 • Wenfeng Liu, Maoguo Gong, Zedong Tang, A. K. Qin
To enhance node representativeness, the output of each convolutional layer is concatenated with the output of the previous layer's readout to form a global context-aware node representation.
no code implementations • 31 Oct 2020 • Tao Xu, Fanhua Shang, Yuanyuan Liu, Hongying Liu, Longjie Shen, Maoguo Gong
For smooth convex loss functions with (non)-smooth regularization, we propose the first differentially private ADMM (DP-ADMM) algorithm with performance guarantee of $(\epsilon,\delta)$-differential privacy ($(\epsilon,\delta)$-DP).
no code implementations • 24 Dec 2020 • Zedong Tang, Fenlong Jiang, Junke Song, Maoguo Gong, Hao Li, Fan Yu, Zidong Wang, Min Wang
Optimizers that further adjust the scale of gradient, such as Adam, Natural Gradient (NG), etc., despite widely concerned and used by the community, are often found poor generalization performance, compared with Stochastic Gradient Descent (SGD).
no code implementations • 24 Mar 2021 • Mulin Chen, Maoguo Gong, Xuelong Li
Non-negative Matrix Factorization (NMF) is one of the most popular techniques for data representation and clustering, and has been widely used in machine learning and data analysis.
no code implementations • 14 Apr 2021 • Yuan Gao, Jiawei Li, Maoguo Gong, Yu Xie, A. K. Qin
Since the existing naive model parameter averaging method is contradictory to the learning paradigm of neural networks, we simulate the process of human cognition and communication, and analogy multi-party learning as a many-to-one knowledge sharing problem.
no code implementations • 14 Apr 2021 • Maoguo Gong, Yuan Gao, Yu Xie, A. K. Qin, Ke Pan, Yew-Soon Ong
The performance of machine learning algorithms heavily relies on the availability of a large amount of training data.
no code implementations • IET Image Processing 2021 • Peipei Zhao, Qiguang Miao, Hang Yao, Xiangzeng Liu, Ruyi Liu, Maoguo Gong
For each feature map, the channel attention module is proposed to explore channel-wise correlation.
Fine-Grained Image Classification Fine-Grained Visual Recognition
no code implementations • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2021 • Hao Li, Maoguo Gong, Mingyang Zhang, Yue Wu
Change detection in heterogeneous remote sensing images is a challenging problem because it is hard to make a direct comparison in the original observation spaces, and most methods rely on a set of manually labeled samples.
1 code implementation • 14 May 2021 • Xiaolong Fan, Maoguo Gong, Yue Wu, Hao Li
Specifically, we first utilize a multi-view representation learning module to better capture both local and global information content across feature and topology views on graphs.
no code implementations • 17 May 2021 • Bin Zhao, Maoguo Gong, Xuelong Li
Motivated by this, we propose to jointly exploit the audio and visual information for the video summarization task, and develop an AudioVisual Recurrent Network (AVRN) to achieve this.
1 code implementation • Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2021 • Zedong Tang, Fenlong Jiang, Maoguo Gong, Hao Li, Yue Wu, Fan Yu, Zidong Wang, Min Wang
For the fully connected layers, by utilizing the low-rank property of Kronecker factors of Fisher information matrix, our method only requires inverting a small matrix to approximate the curvature with desirable accuracy.
1 code implementation • CVPR 2021 • Zedong Tang, Fenlong Jiang, Maoguo Gong, Hao Li, Yue Wu, Fan Yu, Zidong Wang, Min Wang
For the fully connected layers, by utilizing the low-rank property of Kronecker factors of Fisher information matrix, our method only requires inverting a small matrix to approximate the curvature with desirable accuracy.
1 code implementation • 2 Aug 2021 • Junyu Gao, Maoguo Gong, Xuelong Li
To this end, we propose a Dilated Convolutional Swin Transformer (DCST) for congested crowd scenes.
no code implementations • 22 Sep 2021 • Bin Zhao, Maoguo Gong, Xuelong Li
To integrate the two kinds of information, they are encoded in a two-stream scheme, and a multimodal fusion mechanism is developed based on the hierarchical transformer.
no code implementations • 9 Oct 2021 • Xiaolong Zheng, Deyun Zhou, Na Li, Yu Lei, Tao Wu, Maoguo Gong
In the focus search strategy, if there is no knowledge source benefit the optimization of a task, then all knowledge sources in the task's pool are forbidden to be utilized except the task, which helps to improve the performance of the proposed algorithm.
no code implementations • 28 Oct 2021 • Junyu Gao, Maoguo Gong, Xuelong Li
The second is an audio CNN for encoding Log Mel-Spectrogram of audio signals.
no code implementations • 29 Oct 2021 • Maoguo Gong, Yuan Gao, Yue Wu, A. K. Qin
Inspired by the idea of dropout in neural networks, we introduce a network sampling strategy in the multi-party setting, which distributes different subnets of the central model to clients for updating, and the differentiable sampling rates allow each client to extract optimal local architecture from the supernet according to its private data distribution.
no code implementations • 6 May 2022 • Yue Wu, Yibo Liu, Maoguo Gong, Peiran Gong, Hao Li, Zedong Tang, Qiguang Miao, Wenping Ma
The modeling of multi-view point cloud registration as multi-task optimization are twofold.
no code implementations • 9 Aug 2022 • Yiheng Lu, Maoguo Gong, Wei Zhao, Kaiyuan Feng, Hao Li
Therefore, we propose a sensitiveness based method to evaluate the importance of each layer from the perspective of inference accuracy by adding extra damage for the original model.
no code implementations • 13 Aug 2022 • Yiheng Lu, Ziyu Guan, Yaming Yang, Maoguo Gong, Wei Zhao, Kaiyuan Feng
By leveraging the proposed AFIE, the proposed framework is able to yield a stable importance evaluation of each filter no matter whether the original model is trained fully.
1 code implementation • 11 Oct 2022 • Xiaolong Fan, Maoguo Gong, Yue Wu, Mingyang Zhang, Hao Li, Xiangming Jiang
In this paper, we propose a novel Multiview Variational Graph Information Bottleneck (MVGIB) principle to maximize the agreement for common representations and the disagreement for view-specific representations.
no code implementations • 14 Nov 2022 • Mingyang Zhang, Ziqi Di, Maoguo Gong, Yue Wu, Hao Li, Xiangming Jiang
In recent years, research on hyperspectral image (HSI) classification has continuous progress on introducing deep network models, and recently the graph convolutional network (GCN) based models have shown impressive performance.
no code implementations • 12 Dec 2022 • Wu Yue, Peiran Gong, Maoguo Gong, Hangqi Ding, Zedong Tang, Yibo Liu, Wenping Ma, Qiguang Miao
However, most evolving registration methods cannot tackle the local optimum well and they have rarely investigated the success ratio, which implies the probability of not falling into local optima and is closely related to the practicality of the algorithm.
1 code implementation • IEEE Transactions on Geoscience and Remote Sensing 2023 • Tao Lei, Xinzhe Geng, Hailong Ning, Zhiyong Lv, Maoguo Gong, Yaochu Jin, Asoke K. Nandi
First, the existing multiscale feature fusion methods often use redundant feature extraction and fusion strategies, which often lead to high computational costs and memory usage.
Ranked #2 on Change Detection on DSIFN-CD
Building change detection for remote sensing images Change Detection +1
no code implementations • 26 Jul 2023 • Yongzhe Yuan, Yue Wu, Maoguo Gong, Qiguang Miao, A. K. Qin
In this paper, we propose an effective inlier estimation method for unsupervised point cloud registration by capturing geometric structure consistency between the source point cloud and its corresponding reference point cloud copy.
2 code implementations • 11 Dec 2023 • Jiaming Liu, Yue Wu, Maoguo Gong, Qiguang Miao, Wenping Ma, Can Qin
3D Single Object Tracking (SOT) stands a forefront task of computer vision, proving essential for applications like autonomous driving.
no code implementations • 11 Dec 2023 • Yue Wu, Yongzhe Yuan, Xiaolong Fan, Xiaoshui Huang, Maoguo Gong, Qiguang Miao
We propose a new framework that formulates point cloud registration as a denoising diffusion process from noisy transformation to object transformation.
no code implementations • 15 Dec 2023 • Xiaolong Fan, Maoguo Gong, Yue Wu, Zedong Tang, Jieyi Liu
Graph Structure Learning (GSL) has demonstrated considerable potential in the analysis of graph-unknown non-Euclidean data across a wide range of domains.
no code implementations • 22 Feb 2024 • Zhaoyang Wang, Bo Hu, Mingyang Zhang, Jie Li, Leida Li, Maoguo Gong, Xinbo Gao
Firstly, we devise a new diffusion restoration network that leverages the produced enhanced image and noise-containing images, incorporating nonlinear features obtained during the denoising process of the diffusion model, as high-level visual information.
1 code implementation • 27 Feb 2024 • Zhaoyang Wang, Dongyang Li, Mingyang Zhang, Hao Luo, Maoguo Gong
Existing hyperspectral image (HSI) super-resolution (SR) methods struggle to effectively capture the complex spectral-spatial relationships and low-level details, while diffusion models represent a promising generative model known for their exceptional performance in modeling complex relations and learning high and low-level visual features.