no code implementations • 26 Feb 2024 • Qixuan Zheng, Ming Zhang, Hong Yan
To achieve greater accuracy, hypergraph matching algorithms require exponential increases in computational resources.
no code implementations • 9 Feb 2024 • Kecheng Chen, Elena Gal, Hong Yan, Haoliang Li
In this work, we propose to tackle the problem of domain generalization in the context of \textit{insufficient samples}.
no code implementations • 15 Oct 2023 • Long Bai, Shilong Yao, Kun Gao, Yanjun Huang, Ruijie Tang, Hong Yan, Max Q. -H. Meng, Hongliang Ren
Considering that Coupled Dictionary Learning (CDL) method can obtain a reasonable linear mathematical relationship between resource images, we propose a novel CDL-based Synthetic Aperture Radar (SAR) and multispectral pseudo-color fusion method.
1 code implementation • ICCV 2023 • Hong Yan, Yang Liu, Yushen Wei, Zhen Li, Guanbin Li, Liang Lin
Moreover, these methods ignore how to utilize the fine-grained dependencies among different skeleton joints to pre-train an efficient skeleton sequence learning model that can generalize well across different datasets.
2 code implementations • 7 May 2023 • Yushen Wei, Yang Liu, Hong Yan, Guanbin Li, Liang Lin
Our VCSR involves two essential modules: i) the Question-Guided Refiner (QGR) module, which refines consecutive video frames guided by the question semantics to obtain more representative segment features for causal front-door intervention; ii) the Causal Scene Separator (CSS) module, which discovers a collection of visual causal and non-causal scenes based on the visual-linguistic causal relevance and estimates the causal effect of the scene-separating intervention in a contrastive learning manner.
no code implementations • 26 Feb 2023 • Kecheng Chen, Haoliang Li, Renjie Wan, Hong Yan
Under this probabilistic framework, we propose to alleviate the noise distribution shifts between source and target domains via implicit noise modeling schemes in the latent space and image space, respectively.
no code implementations • 22 Feb 2023 • Tiexin Qin, Benjamin Walker, Terry Lyons, Hong Yan, Haoliang Li
Empirical evaluation on a range of dynamic graph representation learning tasks demonstrates the superiority of our proposed approach compared to the baselines.
no code implementations • CVPR 2023 • Xinqi Fan, Xueli Chen, Mingjie Jiang, Ali Raza Shahid, Hong Yan
To overcome this limitation, we proposed a novel MER framework using self-supervised learning to extract facial motion for ME (SelfME).
Micro Expression Recognition Micro-Expression Recognition +2
no code implementations • 21 Sep 2022 • Chong Wu, Zhenan Feng, Houwang Zhang, Hong Yan
Convolutional neural networks (CNNs) are usually used as a backbone to design methods in biomedical image segmentation.
1 code implementation • 7 Sep 2022 • Qiang Xu, Shan Jia, Xinghao Jiang, Tanfeng Sun, Zhe Wang, Hong Yan
Based on the finding that multiple different modules in image acquisition will lead to different sensitivity inconsistencies to the convolutional neural network (CNN)-based rendering in images, we propose a deep texture rendering module for texture difference enhancement and discriminative texture representation.
no code implementations • 26 Apr 2022 • Yang Liu, Yushen Wei, Hong Yan, Guanbin Li, Liang Lin
Visual representation learning is ubiquitous in various real-world applications, including visual comprehension, video understanding, multi-modal analysis, human-computer interaction, and urban computing.
1 code implementation • 17 Apr 2022 • J. de Curtò, I. de Zarzà, Hong Yan, Carlos T. Calafate
We develop a closed-form equation to compute probably good optimal scale factors, as well as the formulation to obtain them by optimization.
1 code implementation • 7 Mar 2022 • Joaquim de Curtò, Irene de Zarzà, Hong Yan, Carlos T. Calafate
In this paper, we bring forward the use of the recently developed Signature Transform as a way to measure the similarity between image distributions and provide detailed acquaintance and extensive evaluations.
Ranked #1 on Image Generation on AFHQ Wild (RMSE Signature metric)
1 code implementation • 1 Jul 2021 • Ming Zhang, Xuefei Zhe, Hong Yan
Experiments are conducted on four commonly-used face datasets under both seen and unseen identities retrieval settings.
no code implementations • 27 Mar 2021 • Jianfeng Cao, Hong Yan
Semantic and instance segmentation algorithms are two general yet distinct image segmentation solutions powered by Convolution Neural Network.
no code implementations • 17 Mar 2021 • Ming Zhang, Hong Yan
Recently, deep classwise hashing introduced a classwise loss supervised by class labels information alternatively; however, we find it still has its drawback.
no code implementations • 28 Dec 2020 • Ali Raza Shahid, Sheheryar Khan, Hong Yan
Dynamic facial expression recognition has many useful applications in social networks, multimedia content analysis, security systems and others.
no code implementations • 24 Aug 2020 • Chuan-Xian Ren, PengFei Ge, Dao-Qing Dai, Hong Yan
KLN can simultaneously learn a more expressive kernel and label prediction distribution, thus, it can be used to improve the classification performance in both supervised and semi-supervised learning scenarios.
1 code implementation • 23 Aug 2020 • Chuan-Xian Ren, You-Wei Luo, Xiao-Lin Xu, Dao-Qing Dai, Hong Yan
Consequently, the crucial point of image set recognition is to mine the intrinsic connection or structural information from the image batches with variations.
no code implementations • 23 Aug 2020 • You-Wei Luo, Chuan-Xian Ren, Dao-Qing Dai, Hong Yan
Second, batch-wise training of deep learning limits the characterization of the global structure.
no code implementations • 14 Jun 2020 • Pengfei Ge, Chuan-Xian Ren, Dao-Qing Dai, Hong Yan
In this paper, we consider a more general application scenario where the label distributions of the source and target domains are not the same.
1 code implementation • 8 May 2020 • Mingjie Jiang, Xinqi Fan, Hong Yan
In this paper, we propose RetinaFaceMask, which is a high-accuracy and efficient face mask detector.
no code implementations • 21 Oct 2019 • Junjun Pan, Michael K. Ng, Ye Liu, Xiongjun Zhang, Hong Yan
In this paper, we study the nonnegative tensor data and propose an orthogonal nonnegative Tucker decomposition (ONTD).
1 code implementation • 31 Jan 2019 • Ming Zhang, Xuefei Zhe, Le Ou-Yang, Shifeng Chen, Hong Yan
Deep hashing models have been proposed as an efficient method for large-scale similarity search.
1 code implementation • 12 Mar 2018 • Xuefei Zhe, Shifeng Chen, Hong Yan
In this regard, we propose a novel deep supervised hashing model to learn more compact class-level similarity preserving binary codes.
1 code implementation • 27 Feb 2018 • Xuefei Zhe, Shifeng Chen, Hong Yan
Deep distance metric learning (DDML), which is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, has achieved encouraging results in many computer vision tasks.$L2$-normalization in the embedding space has been used to improve the performance of several DDML methods.