1 code implementation • 12 Sep 2024 • Hai Wang, Jing-Hao Xue
Secondly, leveraging this embedded noisy latent representation and guided by a target prompt, the seamless tiling translation with spatial control enables the generation of a translated image with identical left and right halves while adhering to the extended input's structure and semantic layout.
no code implementations • 31 May 2024 • Xiaoke Wang, Xiaochen Yang, Rui Zhu, Jing-Hao Xue
Positive-unlabeled (PU) learning aims to train a classifier using the data containing only labeled-positive instances and unlabeled instances.
1 code implementation • 27 May 2024 • Zongkai Zhang, Zidong Xu, Wenming Yang, Qingmin Liao, Jing-Hao Xue
To bridge these gaps, we propose a novel binarized deep convolution (BDC) unit that effectively enhances performance while increasing the number of binarized convolutional layers.
1 code implementation • 10 Apr 2024 • Weihao Xia, Raoul de Charette, Cengiz Öztireli, Jing-Hao Xue
We address prevailing challenges of the brain-powered research, departing from the observation that the literature hardly recover accurate spatial information and require subject-specific models.
1 code implementation • IEEE Transactions on Image Processing 2024 • Woomin Myung, Nan Su, Jing-Hao Xue, Guijin Wang
Graph convolutional networks (GCN) have recently been studied to exploit the graph topology of the human body for skeleton-based action recognition.
Ranked #1 on Skeleton Based Action Recognition on NTU RGB+D 120
1 code implementation • 13 Dec 2023 • Liuxiang Qiu, Si Chen, Yan Yan, Jing-Hao Xue, Da-Han Wang, Shunzhi Zhu
Existing VI-ReID methods ignore high-order structure information of features while being relatively difficult to learn a reasonable common feature space due to the large modality discrepancy between VIS and IR images.
1 code implementation • 12 Dec 2023 • Ziqiang Zhang, Yan Yan, Jing-Hao Xue, Hanzi Wang
SDIC follows a "compensate-and-edit" paradigm and successfully bridges the gap in image details between the original image and the reconstructed/edited image.
1 code implementation • 28 Oct 2023 • Hai Wang, Xiaoyu Xiang, Yuchen Fan, Jing-Hao Xue
To address this issue, we propose a method called StitchDiffusion.
1 code implementation • 3 Oct 2023 • Weihao Xia, Raoul de Charette, Cengiz Öztireli, Jing-Hao Xue
In this work we present DREAM, an fMRI-to-image method for reconstructing viewed images from brain activities, grounded on fundamental knowledge of the human visual system.
1 code implementation • 25 Oct 2022 • Weihao Xia, Jing-Hao Xue
Recent years have seen remarkable progress in deep learning powered visual content creation.
1 code implementation • 23 Aug 2022 • Weihao Xia, Yujiu Yang, Jing-Hao Xue
The entire sequence is seen as discrete-time observations of a continuous trajectory of the initial latent code, by considering each latent code as a moving particle and the latent space as a high-dimensional dynamic system.
1 code implementation • 16 Jul 2022 • Xinyi Zou, Yan Yan, Jing-Hao Xue, Si Chen, Hanzi Wang
Extensive experiments on both in-the-lab and in-the-wild compound expression datasets demonstrate the superiority of our proposed CDNet against several state-of-the-art FSL methods.
cross-domain few-shot learning Facial Expression Recognition +1
no code implementations • 8 Mar 2022 • Xi Weng, Yan Yan, Si Chen, Jing-Hao Xue, Hanzi Wang
In this paper, we present a novel Stage-aware Feature Alignment Network (SFANet) based on the encoder-decoder structure for real-time semantic segmentation of street scenes.
no code implementations • 18 Jan 2022 • Xinyi Zou, Yan Yan, Jing-Hao Xue, Si Chen, Hanzi Wang
To alleviate the problem of limited base classes in our FER task, we propose a novel Emotion Guided Similarity Network (EGS-Net), consisting of an emotion branch and a similarity branch, based on a two-stage learning framework.
cross-domain few-shot learning Facial Expression Recognition +1
no code implementations • 24 Nov 2021 • Jiacheng Chen, Bin-Bin Gao, Zongqing Lu, Jing-Hao Xue, Chengjie Wang, Qingmin Liao
In practice, it can adaptively generate multiple class-agnostic prototypes for query images and learn feature alignment in a self-contrastive manner.
Ranked #48 on Few-Shot Semantic Segmentation on COCO-20i (1-shot)
1 code implementation • 24 Sep 2021 • Yurong Ling, Zijing Liu, Jing-Hao Xue
Dimension reduction plays a pivotal role in analysing high-dimensional data.
2 code implementations • 2 Aug 2021 • Liyang Liu, Shilong Zhang, Zhanghui Kuang, Aojun Zhou, Jing-Hao Xue, Xinjiang Wang, Yimin Chen, Wenming Yang, Qingmin Liao, Wayne Zhang
Our method can be used to prune any structures including those with coupled channels.
Ranked #4 on Network Pruning on ImageNet
no code implementations • CVPR 2021 • Ying Shu, Yan Yan, Si Chen, Jing-Hao Xue, Chunhua Shen, Hanzi Wang
First, three auxiliary tasks, consisting of a Patch Rotation Task (PRT), a Patch Segmentation Task (PST), and a Patch Classification Task (PCT), are jointly developed to learn the spatial-semantic relationship from large-scale unlabeled facial data.
Ranked #3 on Facial Attribute Classification on LFWA
no code implementations • 17 May 2021 • Xiaoxu Li, Xiaochen Yang, Zhanyu Ma, Jing-Hao Xue
Few-shot image classification is a challenging problem that aims to achieve the human level of recognition based only on a small number of training images.
no code implementations • 19 Apr 2021 • Jiacheng Chen, Bin-Bin Gao, Zongqing Lu, Jing-Hao Xue, Chengjie Wang, Qingmin Liao
To this end, we generate self-contrastive background prototypes directly from the query image, with which we enable the construction of complete sample pairs and thus a complementary and auxiliary segmentation task to achieve the training of a better segmentation model.
2 code implementations • 18 Apr 2021 • Weihao Xia, Yujiu Yang, Jing-Hao Xue, Baoyuan Wu
To be specific, we propose a brand new paradigm of text-guided image generation and manipulation based on the superior characteristics of a pretrained GAN model.
Ranked #5 on Text-to-Image Generation on Multi-Modal-CelebA-HQ
1 code implementation • 14 Jan 2021 • Weihao Xia, Yulun Zhang, Yujiu Yang, Jing-Hao Xue, Bolei Zhou, Ming-Hsuan Yang
GAN inversion aims to invert a given image back into the latent space of a pretrained GAN model, for the image to be faithfully reconstructed from the inverted code by the generator.
3 code implementations • ICLR 2021 • Liyang Liu, Yi Li, Zhanghui Kuang, Jing-Hao Xue, Yimin Chen, Wenming Yang, Qingmin Liao, Wayne Zhang
Multi-task learning (MTL) has been widely used in representation learning.
5 code implementations • CVPR 2021 • Weihao Xia, Yujiu Yang, Jing-Hao Xue, Baoyuan Wu
In this work, we propose TediGAN, a novel framework for multi-modal image generation and manipulation with textual descriptions.
Ranked #6 on Text-to-Image Generation on Multi-Modal-CelebA-HQ
1 code implementation • NeurIPS 2020 • Mingzhi Dong, Xiaochen Yang, Rui Zhu, Yujiang Wang, Jing-Hao Xue
Metric learning aims to learn a distance measure that can benefit distance-based methods such as the nearest neighbour (NN) classifier.
1 code implementation • 29 Nov 2020 • Xiaoxu Li, Jijie Wu, Zhuo Sun, Zhanyu Ma, Jie Cao, Jing-Hao Xue
Motivated by this, we propose a so-called \textit{Bi-Similarity Network} (\textit{BSNet}) that consists of a single embedding module and a bi-similarity module of two similarity measures.
no code implementations • 17 Nov 2020 • Jiyang Xie, Zhanyu Ma, Jing-Hao Xue, Guoqiang Zhang, Jun Guo
In the DS-UI, we combine the classifier of a DNN, i. e., the last fully-connected (FC) layer, with a mixture of Gaussian mixture models (MoGMM) to obtain an MoGMM-FC layer.
1 code implementation • 11 Oct 2020 • Jiyang Xie, Zhanyu Ma, and Jianjun Lei, Guoqiang Zhang, Jing-Hao Xue, Zheng-Hua Tan, Jun Guo
Due to lack of data, overfitting ubiquitously exists in real-world applications of deep neural networks (DNNs).
1 code implementation • 9 Oct 2020 • Weihao Xia, Yujiu Yang, Jing-Hao Xue, Wensen Feng
The encoder maps images into a well-disentangled and hierarchically-organized latent space.
1 code implementation • 27 Jun 2020 • Xiaoxu Li, Liyun Yu, Xiaochen Yang, Zhanyu Ma, Jing-Hao Xue, Jie Cao, Jun Guo
Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small.
1 code implementation • 10 Jun 2020 • Xiaochen Yang, Yiwen Guo, Mingzhi Dong, Jing-Hao Xue
Many existing methods consider maximizing or at least constraining a distance margin in the feature space that separates similar and dissimilar pairs of instances to guarantee their generalization ability.
no code implementations • 22 May 2020 • Xiaoxu Li, Zhuo Sun, Jing-Hao Xue, Zhanyu Ma
Few-shot meta-learning has been recently reviving with expectations to mimic humanity's fast adaption to new concepts based on prior knowledge.
1 code implementation • 20 Apr 2020 • Xiaoxu Li, Dongliang Chang, Zhanyu Ma, Zheng-Hua Tan, Jing-Hao Xue, Jie Cao, Jingyi Yu, Jun Guo
A deep neural network of multiple nonlinear layers forms a large function space, which can easily lead to overfitting when it encounters small-sample data.
no code implementations • 28 Mar 2020 • Juncheng Zhang, Qingmin Liao, Shaojun Liu, Haoyu Ma, Wenming Yang, Jing-Hao Xue
In this letter, we introduce a large and realistic multi-focus dataset called Real-MFF, which contains 710 pairs of source images with corresponding ground truth images.
no code implementations • 27 Feb 2020 • Jiarong Chen, Zongqing Lu, Jing-Hao Xue, Qingmin Liao
Depthwise convolution has gradually become an indispensable operation for modern efficient neural networks and larger kernel sizes ($\ge5$) have been applied to it recently.
no code implementations • 10 Feb 2020 • Longbiao Mao, Yan Yan, Jing-Hao Xue, Hanzi Wang
Two different network architectures are respectively designed to extract features for two groups of attributes, and a novel dynamic weighting scheme is proposed to automatically assign the loss weight to each facial attribute during training.
no code implementations • 2 Nov 2019 • Weihao Xia, Zhanglin Cheng, Yujiu Yang, Jing-Hao Xue
Most state-of-the-art semantic segmentation approaches only achieve high accuracy in good conditions.
1 code implementation • 2 Nov 2019 • Weihao Xia, Yujiu Yang, Jing-Hao Xue
Image-to-image translation has drawn great attention during the past few years.
no code implementations • 2 Nov 2019 • Weihao Xia, Yujiu Yang, Jing-Hao Xue, Jing Xiao
Human fingerprints are detailed and nearly unique markers of human identity.
no code implementations • 1 Nov 2019 • Weihao Xia, Yujiu Yang, Jing-Hao Xue
Image generation has received increasing attention because of its wide application in security and entertainment.
2 code implementations • 29 Oct 2019 • Haoyu Ma, Qingmin Liao, Juncheng Zhang, Shaojun Liu, Jing-Hao Xue
Based on this {\alpha}-matte defocus model and the generated data, a cascaded boundary aware convolutional network termed MMF-Net is proposed and trained, aiming to achieve clearer fusion results around the FDB.
no code implementations • 29 Oct 2019 • Kazuhiro Fukui, Naoya Sogi, Takumi Kobayashi, Jing-Hao Xue, Atsuto Maki
To avoid the difficulty, we first introduce geometrical Fisher discriminant analysis (gFDA) based on a simplified Fisher criterion.
1 code implementation • 9 Sep 2019 • Wenming Yang, Xuechen Zhang, Yapeng Tian, Wei Wang, Jing-Hao Xue, Qingmin Liao
In this paper, we develop a concise but efficient network architecture called linear compressing based skip-connecting network (LCSCNet) for image super-resolution.
Ranked #17 on Image Super-Resolution on Set14 - 3x upscaling
no code implementations • 14 Mar 2019 • Naoya Sogi, Rui Zhu, Jing-Hao Xue, Kazuhiro Fukui
Moreover, to enhance the framework, we introduce a discriminant space that maximizes the between-class variance (gaps) and minimizes the within-class variance of the projected convex cones onto the discriminant space, similar to the Fisher discriminant analysis.
no code implementations • 26 Feb 2019 • Guijin Wang, Cairong Zhang, Xinghao Chen, Xiangyang Ji, Jing-Hao Xue, Hang Wang
To mitigate these limitations and promote further research on hand pose estimation from stereo images, we propose a new large-scale binocular hand pose dataset called THU-Bi-Hand, offering a new perspective for fingertip localization.
1 code implementation • 9 Aug 2018 • Wenming Yang, Xuechen Zhang, Yapeng Tian, Wei Wang, Jing-Hao Xue
Single image super-resolution (SISR) is a notoriously challenging ill-posed problem, which aims to obtain a high-resolution (HR) output from one of its low-resolution (LR) versions.
no code implementations • 28 Jul 2018 • Jiyang Xie, Jiaxin Guo, Zhanyu Ma, Jing-Hao Xue, Qie Sun, Hailong Li, Jun Guo
ENN and ARIMA are used to predict seasonal and trend components, respectively.
no code implementations • 8 Jul 2018 • Jiyang Xie, Zhanyu Ma, Guo-Qiang Zhang, Jing-Hao Xue, Jen-Tzung Chien, Zhiqing Lin, Jun Guo
In order to explicitly characterize the nonnegative L1-norm constraint of the parameters, we further approximate the true posterior distribution by a Dirichlet distribution.
no code implementations • 9 Feb 2018 • Mingzhi Dong, Yujiang Wang, Xiaochen Yang, Jing-Hao Xue
The performance of distance-based classifiers heavily depends on the underlying distance metric, so it is valuable to learn a suitable metric from the data.
no code implementations • 9 Feb 2018 • Mingzhi Dong, Xiaochen Yang, Yang Wu, Jing-Hao Xue
In this paper, we propose the Lipschitz margin ratio and a new metric learning framework for classification through maximizing the ratio.
no code implementations • 30 May 2017 • Zhanyu Ma, Jing-Hao Xue, Arne Leijon, Zheng-Hua Tan, Zhen Yang, Jun Guo
In this paper, we propose novel strategies for neutral vector variable decorrelation.