1 code implementation • COLING 2022 • Heng-yang Lu, Chenyou Fan, Jun Yang, Cong Hu, Wei Fang, Xiao-Jun Wu
Based on the predicted P2P, four effective strategies are introduced to show the BDA performance.
no code implementations • 2 Dec 2024 • Xiao-Jun Wu, Cai-Jun Zhao, Chun Meng, Hang Wang
This paper Proposes a novel cervical cancer dual-stained image recognition (DSIR-YOLO) model based on an YOLOv5.
no code implementations • 16 Nov 2024 • Huan Kang, Hui Li, Tianyang Xu, Rui Wang, Xiao-Jun Wu, Josef Kittler
Euclidean representation learning methods have achieved commendable results in image fusion tasks, which can be attributed to their clear advantages in handling with linear space.
no code implementations • 23 Sep 2024 • Wenhua Dong, Xiao-Jun Wu, ZhenHua Feng, Sara Atito, Muhammad Awais, Josef Kittler
In most existing multi-view modeling scenarios, cross-view correspondence (CVC) between instances of the same target from different views, like paired image-text data, is a crucial prerequisite for effortlessly deriving a consistent representation.
1 code implementation • 28 Aug 2024 • Yanglin Deng, Tianyang Xu, Chunyang Cheng, Xiao-Jun Wu, Josef Kittler
In this work, a lightweight Distilled Mini-Model with a Dynamic Refresh strategy (MMDRFuse) is proposed to achieve this objective.
no code implementations • 15 Jul 2024 • Ziheng Chen, Yue Song, Xiao-Jun Wu, Gaowen Liu, Nicu Sebe
Global Covariance Pooling (GCP) has been demonstrated to improve the performance of Deep Neural Networks (DNNs) by exploiting second-order statistics of high-level representations.
1 code implementation • 8 Jul 2024 • Rongchang Li, ZhenHua Feng, Tianyang Xu, Linze Li, Xiao-Jun Wu, Muhammad Awais, Sara Atito, Josef Kittler
For evaluating the task, we construct a new benchmark, Something-composition (Sth-com), based on the widely used Something-Something V2 dataset.
no code implementations • 2 Jul 2024 • Ziheng Chen, Yue Song, Xiao-Jun Wu, Nicu Sebe
Further, by Cholesky decomposition, the proposed deformed metrics and gyro structures are pulled back to SPD manifolds.
1 code implementation • 15 Jun 2024 • Hui Li, Xiao-Jun Wu
With the trained CAM, features extracted from two modalities are integrated into one fused feature in which the complementary information is enhanced and the redundant features are reduced.
no code implementations • 7 Jun 2024 • Hui Li, Haolong Ma, Chunyang Cheng, Zhongwei Shen, Xiaoning Song, Xiao-Jun Wu
To address this issue, a continuous decomposition-based fusion framework (Conti-Fuse) is proposed.
1 code implementation • 8 May 2024 • Pengcheng Shao, Tianyang Xu, Zhangyong Tang, Linze Li, Xiao-Jun Wu, Josef Kittler
There is currently strong interest in improving visual object tracking by augmenting the RGB modality with the output of a visual event camera that is particularly informative about the scene motion.
1 code implementation • 30 Apr 2024 • Zhangyong Tang, Tianyang Xu, ZhenHua Feng, XueFeng Zhu, He Wang, Pengcheng Shao, Chunyang Cheng, Xiao-Jun Wu, Muhammad Awais, Sara Atito, Josef Kittler
We propose a new method based on a mixture of experts, namely MoETrack, as a baseline fusion strategy.
Ranked #3 on
Rgb-T Tracking
on GTOT
no code implementations • 25 Apr 2024 • Cong Wu, Xiao-Jun Wu, Tianyang Xu, Josef Kittler
Pooling is a crucial operation in computer vision, yet the unique structure of skeletons hinders the application of existing pooling strategies to skeleton graph modelling.
1 code implementation • 21 Dec 2023 • Chunyang Cheng, Tianyang Xu, Xiao-Jun Wu, Hui Li, Xi Li, Zhangyong Tang, Josef Kittler
Advanced image fusion methods are devoted to generating the fusion results by aggregating the complementary information conveyed by the source images.
no code implementations • 28 Nov 2023 • Rui Wang, Xiao-Jun Wu, Hui Li, Josef Kittler
Symmetric positive definite (SPD) matrix has been demonstrated to be an effective feature descriptor in many scientific areas, as it can encode spatiotemporal statistics of the data adequately on a curved Riemannian manifold, i. e., SPD manifold.
no code implementations • 7 Nov 2023 • Jun Sun, Zhongjie Mao, Chao Li, Chao Zhou, Xiao-Jun Wu
The common framework among recent approaches is to train the model on a large amount of unlabelled data with consistency regularization to constrain the model predictions to be invariant to input perturbation.
no code implementations • 11 Sep 2023 • Cong Wu, Xiao-Jun Wu, Josef Kittler, Tianyang Xu, Sara Atito, Muhammad Awais, ZhenHua Feng
Contrastive learning has achieved great success in skeleton-based action recognition.
1 code implementation • 4 Sep 2023 • Zhangyong Tang, Tianyang Xu, XueFeng Zhu, Xiao-Jun Wu, Josef Kittler
In this context, we seek to uncover the potential of harnessing generative techniques to address the critical challenge, information fusion, in multi-modal tracking.
Ranked #15 on
Rgb-T Tracking
on LasHeR
no code implementations • 9 Aug 2023 • Li-Wei Li, Jun Sun, Chao Li, Wei Fang, Vasile Palade, Xiao-Jun Wu
Then, the correlations between the two types of diversities and the search performance are tested and analyzed on several benchmark functions, and the distance-to-average-point diversity is showed to have stronger association with the search performance during the evolving processes.
1 code implementation • 27 Jun 2023 • Xue-Feng Zhu, Tianyang Xu, Jian Zhao, Jia-Wei Liu, Kai Wang, Gang Wang, Jianan Li, Qiang Wang, Lei Jin, Zheng Zhu, Junliang Xing, Xiao-Jun Wu
Still, previous works have simplified such an anti-UAV task as a tracking problem, where the prior information of UAVs is always provided; such a scheme fails in real-world anti-UAV tasks (i. e. complex scenes, indeterminate-appear and -reappear UAVs, and real-time UAV surveillance).
1 code implementation • 10 May 2023 • Chunyang Cheng, Tianyang Xu, Xiao-Jun Wu, Hui Li, Xi Li, Josef Kittler
We argue that there is a scope to improve the fusion performance with the help of the FusionBooster, a model specifically designed for the fusion task.
1 code implementation • 11 Apr 2023 • Hui Li, Tianyang Xu, Xiao-Jun Wu, Jiwen Lu, Josef Kittler
In particular we adopt a learnable representation approach to the fusion task, in which the construction of the fusion network architecture is guided by the optimisation algorithm producing the learnable model.
no code implementations • 26 Mar 2023 • Ziheng Chen, Yue Song, Tianyang Xu, Zhiwu Huang, Xiao-Jun Wu, Nicu Sebe
Symmetric Positive Definite (SPD) matrices have received wide attention in machine learning due to their intrinsic capacity to encode underlying structural correlation in data.
no code implementations • 23 Dec 2022 • Yaozong Mo, ChaoFeng Li, Wenqi Ren, Shaopeng Shang, Wenwu Wang, Xiao-Jun Wu
In this work, we propose a Prior map Guided CycleGAN (PG-CycleGAN) for defogging of images with overwater scenes.
1 code implementation • 21 Sep 2022 • Qingbei Guo, Xiao-Jun Wu, Zhiquan Feng, Tianyang Xu, Cong Hu
To tackle this issue, we first introduce a new attention dimension, i. e., depth, in addition to existing attention dimensions such as channel, spatial, and branch, and present a novel selective depth attention network to symmetrically handle multi-scale objects in various vision tasks.
1 code implementation • 21 Aug 2022 • Xue-Feng Zhu, Tianyang Xu, Zhangyong Tang, Zucheng Wu, Haodong Liu, Xiao Yang, Xiao-Jun Wu, Josef Kittler
To demonstrate the benefits of training on a larger RGB-D data set in general, and RGBD1K in particular, we develop a transformer-based RGB-D tracker, named SPT, as a baseline for future visual object tracking studies using the new dataset.
no code implementations • 30 Jun 2022 • Xu Song, Tianyu Shen, Hui Li, Xiao-Jun Wu
The detailed parts are fused employing a nuclear-norm operation, while the basic parts are fused using an average strategy.
no code implementations • 16 Jun 2022 • Rui Wang, Xiao-Jun Wu, Ziheng Chen, Tianyang Xu, Josef Kittler
Image set-based visual classification methods have achieved remarkable performance, via characterising the image set in terms of a non-singular covariance matrix on a symmetric positive definite (SPD) manifold.
1 code implementation • 12 May 2022 • Shuang Wu, Xiaoning Song, ZhenHua Feng, Xiao-Jun Wu
To deal with this issue, we advocate a novel lexical enhancement method, InterFormer, that effectively reduces the amount of computational and memory costs by constructing non-flat lattices.
Ranked #9 on
Chinese Named Entity Recognition
on Resume NER
Chinese Named Entity Recognition
named-entity-recognition
+2
no code implementations • 28 Jan 2022 • Yu-Hong Cai, Xiao-Jun Wu, Zhe Chen
However, methods based on this technique ignore the pressure on a single transformation matrix due to the complex information contained in the data.
no code implementations • 26 Jan 2022 • Haoming Zhang, Xiao-Jun Wu, Tianyang Xu, Donglin Zhang
Thirdly, we introduce a similarity preservation term, thus our model can compensate for the shortcomings of insufficient use of discriminative data and better preserve the semantically structural information within each modality.
no code implementations • 26 Jan 2022 • Zhancheng Zhang, Yuanhao Gao, Mengyu Xiong, Xiaoqing Luo, Xiao-Jun Wu
Background: Leaning redundant and complementary relationships is a critical step in the human visual system.
no code implementations • 26 Jan 2022 • Xiaoqing Luo, Yuting Jiang, Anqi Wang, Zhancheng Zhang, Xiao-Jun Wu
The traditional two-state hidden Markov model divides the high frequency coefficients only into two states (large and small states).
1 code implementation • 25 Jan 2022 • Dongyu Rao, Xiao-Jun Wu, Tianyang Xu
The end-to-end image fusion framework has achieved promising performance, with dedicated convolutional networks aggregating the multi-modal local appearance.
Generative Adversarial Network
Infrared And Visible Image Fusion
1 code implementation • 25 Jan 2022 • Ziheng Chen, Tianyang Xu, Xiao-Jun Wu, Rui Wang, Zhiwu Huang, Josef Kittler
The Symmetric Positive Definite (SPD) matrices have received wide attention for data representation in many scientific areas.
no code implementations • 25 Jan 2022 • Dongyu Rao, Xiao-Jun Wu, Tianyang Xu, Guoyang Chen
We propose a feature mutual mapping fusion module and dual-branch multi-scale autoencoder.
no code implementations • 23 Jan 2022 • Xue-Feng Zhu, Tianyang Xu, Xiao-Jun Wu
The development of visual object tracking has continued for decades.
no code implementations • 23 Jan 2022 • Zhangyong Tang, Tianyang Xu, Xiao-Jun Wu
This survey can be treated as a look-up-table for researchers who are concerned about RGBT tracking.
1 code implementation • 23 Jan 2022 • He-Feng Yin, Xiao-Jun Wu, Xiaoning Song
The second order image gradient orientations (SOIGO) can mitigate the adverse effect of noises in face images.
1 code implementation • 22 Jan 2022 • Zhangyong Tang, Tianyang Xu, Xiao-Jun Wu
Specifically, different from traditional Siamese trackers, which only obtain one search image during the process of picking up template-search image pairs, an extra search sample adjacent to the original one is selected to predict the temporal transformation, resulting in improved robustness of tracking performance. As for multi-modal tracking, constrained to the limited RGBT datasets, the adaptive fusion sub-network is appended to our method at the decision level to reflect the complementary characteristics contained in two modalities.
no code implementations • 22 Jan 2022 • Li Chu, Rui Wang, Xiao-Jun Wu
Recent advances illustrate that how to effectively model these nonlinear variational information and learn invariant representations is an open challenge in the community of computer vision and pattern recognition To this end, we try to design a new algorithm to handle this problem.
1 code implementation • 21 Jan 2022 • Zhangyong Tang, Tianyang Xu, Hui Li, Xiao-Jun Wu, XueFeng Zhu, Josef Kittler
The effectiveness of the proposed decision-level fusion strategy owes to a number of innovative contributions, including a dynamic weighting of the RGB and TIR contributions and a linear template update operation.
no code implementations • 29 Dec 2021 • Xu Song, Yongbiao Xiao, Hui Li, Xiao-Jun Wu, Jun Sun, Vasile Palade
The encoder based on Res2Net is utilized for extracting multi-scale features from the input image.
no code implementations • 22 Oct 2021 • Jianjun Liu, Zebin Wu, Liang Xiao, Xiao-Jun Wu
Inspired by the specific properties of model, we make the first attempt to design a model inspired deep network for HSI super-resolution in an unsupervised manner.
no code implementations • 12 Oct 2021 • Rongchang Li, Xiao-Jun Wu, Tianyang Xu
In this paper, we first propose to transform a video sequence into a graph to obtain direct long-term dependencies among temporal frames.
no code implementations • 17 Aug 2021 • Donglin Zhang, Xiao-Jun Wu, He-Feng Yin, Josef Kittler
To this end, we develop a novel Multiple hash cOdes jOint learNing method (MOON) for cross-media retrieval.
1 code implementation • 7 Mar 2021 • Hui Li, Xiao-Jun Wu, Josef Kittler
The most difficult part of the design is to choose an appropriate strategy to generate the fused image for a specific task in hand.
1 code implementation • 3 Mar 2021 • Qingbei Guo, Xiao-Jun Wu, Josef Kittler, Zhiquan Feng
To address this computational complexity issue, we introduce a novel \emph{architecture parameterisation} based on scaled sigmoid function, and propose a general \emph{Differentiable Neural Architecture Learning} (DNAL) method to optimize the neural architecture without the need to evaluate candidate neural networks.
no code implementations • 21 Feb 2021 • Yu Fu, Xiao-Jun Wu, Josef Kittler
In this paper, we apply the image decomposition network to the image fusion task.
2 code implementations • 24 Jan 2021 • Yu Fu, Xiao-Jun Wu
Deep learning is a rapidly developing approach in the field of infrared and visible image fusion.
Generative Adversarial Network
Infrared And Visible Image Fusion
+1
1 code implementation • 29 Sep 2020 • Qingbei Guo, Xiao-Jun Wu, Josef Kittler, Zhiquan Feng
To tackle this issue, we propose a novel method of designing self-grouping convolutional neural networks, called SG-CNN, in which the filters of each convolutional layer group themselves based on the similarity of their importance vectors.
no code implementations • 25 Jul 2020 • Jingqiao Zhao, Zhen-Hua Feng, Qiuqiang Kong, Xiaoning Song, Xiao-Jun Wu
This paper presents a Depthwise Disout Convolutional Neural Network (DD-CNN) for the detection and classification of urban acoustic scenes.
1 code implementation • 10 Jul 2020 • He-Feng Yin, Xiao-Jun Wu, Zhen-Hua Feng, Josef Kittler
Moreover, ANCR introduces an affine constraint to better represent the data from affine subspaces.
1 code implementation • 1 Jul 2020 • Hui Li, Xiao-Jun Wu, Tariq Durrani
In our proposed fusion strategy, spatial attention models and channel attention models are developed that describe the importance of each spatial position and of each channel with deep features.
no code implementations • 27 May 2020 • Tianyang Xu, Zhen-Hua Feng, Xiao-Jun Wu, Josef Kittler
To this end, we propose a failure-aware system, realised by a Quality Prediction Network (QPN), based on convolutional and LSTM modules in the decision stage, enabling online reporting of potential tracking failures.
1 code implementation • ECCV 2020 • Lingteng Qiu, Xuanye Zhang, Yan-ran Li, Guanbin Li, Xiao-Jun Wu, Zixiang Xiong, Xiaoguang Han, Shuguang Cui
Although occlusion widely exists in nature and remains a fundamental challenge for pose estimation, existing heatmap-based approaches suffer serious degradation on occlusions.
no code implementations • 9 Feb 2020 • Zi-Qi Li, Jun Sun, Xiao-Jun Wu, He-Feng Yin
Recent years have witnessed the success of dictionary learning (DL) based approaches in the domain of pattern classification.
no code implementations • 4 Feb 2020 • Huai-Shui Tong, Xiao-Jun Wu, Hui Li
This paper presents an improved dual channel pulse coupled neural network (IDC-PCNN) model for image fusion.
no code implementations • 21 Jan 2020 • Ning Yuan, Xiao-Jun Wu, He-Feng Yin
The method CSKDA needs to choose a proper kernel function through many experiments, while the new method could learn the kernel from data automatically which could save a lot of time and have the robust performance.
1 code implementation • 20 Jan 2020 • Zi-Qi Li, Jun Sun, Xiao-Jun Wu, He-Feng Yin
Firstly, the coefficients of the test sample are obtained by SRC and CCRC, respectively.
no code implementations • 24 Dec 2019 • Yi-Xuan Wang, Xiao-Jun Wu, Xue-Feng Zhu
With the guaranteed discrimination and efficiency of spatial appearance model, Discriminative Correlation Filters (DCF-) based tracking methods have achieved outstanding performance recently.
no code implementations • 24 Dec 2019 • Fei Feng, Xiao-Jun Wu, Tianyang Xu, Josef Kittler, Xue-Feng Zhu
In the response map obtained for the previous frame by the CF algorithm, we adaptively find the image blocks that are similar to the target and use them as negative samples.
no code implementations • 23 Dec 2019 • Xing Liu, Xiao-Jun Wu, Zi-Qi Li
In this paper, two novel methods: 2DR1-PCA and 2DL1-PCA are proposed for face recognition.
no code implementations • 23 Dec 2019 • Xing Liu, Xiao-Jun Wu, Zhen Liu, He-Feng Yin
The technology of face recognition has made some progress in recent years.
no code implementations • 21 Dec 2019 • Wen-Jin Fu, Xiao-Jun Wu, He-Feng Yin, Wen-Bo Hu
Recently, sparse subspace clustering has been a valid tool to deal with high-dimensional data.
no code implementations • 17 Dec 2019 • Wen Zhao, Xiao-Jun Wu, He-Feng Yin, Zi-Qi Li
Collaborative representation based classification (CRC) method is exploited in our proposed method which has closed-form solution.
no code implementations • 17 Dec 2019 • Kai Xu, Xiao-Jun Wu, Wen-Bo Hu
Based on further studying the low-rank subspace clustering (LRSC) and L2-graph subspace clustering algorithms, we propose a F-graph subspace clustering algorithm with a symmetric constraint (FSSC), which constructs a new objective function with a symmetric constraint basing on F-norm, whose the most significant advantage is to obtain a closed-form solution of the coefficient matrix.
no code implementations • 17 Dec 2019 • Ya-Qiong Zhang, Xiao-Jun Wu, Hui Li
For three source images, a joint region segmentation method based on segmentation of two images is used to obtain the final segmentation result.
no code implementations • 10 Dec 2019 • Pei Xie, He-Feng Yin, Xiao-Jun Wu
Face recognition remains a hot topic in computer vision, and it is challenging to tackle the problem that both the training and testing images are corrupted.
1 code implementation • 6 Dec 2019 • He-Feng Yin, Xiao-Jun Wu, Josef Kittler
First, a low-rank representation is introduced to handle the possible contamination of the training as well as test data.
no code implementations • 5 Dec 2019 • Tianyang Xu, Zhen-Hua Feng, Xiao-Jun Wu, Josef Kittler
Recent visual object tracking methods have witnessed a continuous improvement in the state-of-the-art with the development of efficient discriminative correlation filters (DCF) and robust deep neural network features.
no code implementations • 23 Nov 2019 • He-Feng Yin, Xiao-Jun Wu, Josef Kittler, Zhen-Hua Feng
To counteract this problem, we propose an approach that learns Representation with Block-Diagonal Structure (RBDS) for robust image recognition.
1 code implementation • 22 Nov 2019 • He-Feng Yin, Xiao-Jun Wu, Su-Gen Chen
In this paper, we propose a locality constraint dictionary learning with support vector discriminative term (LCDL-SV), in which the locality information is preserved by employing the graph Laplacian matrix of the learned dictionary.
1 code implementation • 22 Nov 2019 • He-Feng Yin, Xiao-Jun Wu
Representation based classification method (RBCM) remains one of the hottest topics in the community of pattern recognition, and the recently proposed non-negative representation based classification (NRC) achieved impressive recognition results in various classification tasks.
no code implementations • IEEE International Conference on Computer Vision (ICCV), 2019 2019 • Cong Wu, Xiao-Jun Wu, Josef Kittler
In order to capture the rich spatiotemporal information and utilize features more effectively, we introduce a spatial residual layer and a dense connection block enhanced spatial temporal graph convolutional network.
Ranked #56 on
Skeleton Based Action Recognition
on NTU RGB+D
no code implementations • 19 Sep 2019 • Cong Hu, Zhen-Hua Feng, Xiao-Jun Wu, Josef Kittler
To be more specific, the encoder-decoder structured generator is used to learn a pose disentangled face representation, and the encoder-decoder structured discriminator is tasked to perform real/fake classification, face reconstruction, determining identity and estimating face pose.
2 code implementations • 16 Sep 2019 • Kai-Xuan Chen, Xiao-Jun Wu, Jie-Yi Ren, Rui Wang, Josef Kittler
We consider a family of structural descriptors for visual data, namely covariance descriptors (CovDs) that lie on a non-linear symmetric positive definite (SPD) manifold, a special type of Riemannian manifolds.
no code implementations • 6 Aug 2019 • Rui Wang, Xiao-Jun Wu, Josef Kittler
Specifically, the covariance matrix, linear subspace, and Gaussian distribution are applied for set representation simultaneously.
1 code implementation • ICCV 2019 • Tianyang Xu, Zhen-Hua Feng, Xiao-Jun Wu, Josef Kittler
We propose a new Group Feature Selection method for Discriminative Correlation Filters (GFS-DCF) based visual object tracking.
Ranked #1 on
Visual Object Tracking
on VOT2017
no code implementations • 13 Jun 2019 • Pengyuan Lyu, Zhicheng Yang, Xinhang Leng, Xiao-Jun Wu, Ruiyu Li, Xiaoyong Shen
Irregular scene text, which has complex layout in 2D space, is challenging to most previous scene text recognizers.
no code implementations • 14 May 2019 • Zhe Chen, Xiao-Jun Wu, Josef Kittler
Only learning one projection matrix from original samples to the corresponding binary labels is too strict and will consequentlly lose some intrinsic geometric structures of data.
no code implementations • 26 Mar 2019 • Jun Yu, Xiao-Jun Wu
With the advantage of low storage cost and high efficiency, hashing learning has received much attention in the domain of Big Data.
no code implementations • 26 Mar 2019 • Jun Yu, Xiao-Jun Wu
Our model not only considers the inter-modality correlation by maximizing the kernel correlation but also preserves the semantically structural information within each modality.
no code implementations • 19 Mar 2019 • Zhe Chen, Xiao-Jun Wu, Josef Kittler
In this paper, we propose a non-negative representation based discriminative dictionary learning algorithm (NRDL) for multicategory face classification.
no code implementations • 19 Mar 2019 • Zhe Chen, Xiao-Jun Wu, Josef Kittler
To solve above problems, we propose a low-rank discriminative least squares regression model (LRDLSR) for multi-class image classification.
1 code implementation • 19 Mar 2019 • Zhe Chen, Xiao-Jun Wu, Josef Kittler
On one hand, the Fisher criterion improves the intra-class compactness of the relaxed labels during relaxation learning.
no code implementations • 6 Dec 2018 • Jun Yu, Xiao-Jun Wu, Josef Kittler
With the advantage of low storage cost and high retrieval efficiency, hashing techniques have recently been an emerging topic in cross-modal similarity search.
no code implementations • 13 Nov 2018 • Lei Jiang, Xiao-Jun Wu, Josef Kittler
Our method solves the problem of face reconstruction of a single image of a traditional method in a large pose, works on arbitrary Pose and Expressions, greatly improves the accuracy of reconstruction.
2 code implementations • 6 Nov 2018 • Hui Li, Xiao-Jun Wu, Josef Kittler
We develop a novel image fusion framework based on MDLatLRR, which is used to decompose source images into detail parts(salient features) and base parts.
no code implementations • 16 Aug 2018 • Yu Yanga, Xiao-Jun Wu, Josef Kittler
In this paper we show that landmark weighting is instrumental to improve the accuracy of shape reconstruction and propose a novel 3D Morphable Model Fitting method.
no code implementations • 13 Aug 2018 • Jun Yu, Xiao-Jun Wu, Josef Kittler
Many hashing methods based on a single view have been extensively studied for information retrieval.
1 code implementation • 30 Jul 2018 • Tianyang Xu, Zhen-Hua Feng, Xiao-Jun Wu, Josef Kittler
The key innovations of the proposed method include adaptive spatial feature selection and temporal consistent constraints, with which the new tracker enables joint spatial-temporal filter learning in a lower dimensional discriminative manifold.
no code implementations • 28 Jun 2018 • Rui Wang, Xiao-Jun Wu, Kai-Xuan Chen, Josef Kittler
The core of the method is a new discriminant function for metric learning and dimensionality reduction.
no code implementations • 19 Jun 2018 • Jun Yu, Xiao-Jun Wu, Josef Kittler
Recently, hashing techniques have gained importance in large-scale retrieval tasks because of their retrieval speed.
3 code implementations • 19 Jun 2018 • Hui Li, Xiao-Jun Wu, Tariq S. Durrani
Feature extraction and processing tasks play a key role in Image Fusion, and the fusion performance is directly affected by the different features and processing methods undertaken.
no code implementations • 16 Jun 2018 • Kai-Xuan Chen, Xiao-Jun Wu
In the domain of pattern recognition, using the SPD (Symmetric Positive Definite) matrices to represent data and taking the metrics of resulting Riemannian manifold into account have been widely used for the task of image set classification.
no code implementations • 16 Jun 2018 • Kai-Xuan Chen, Xiao-Jun Wu, Rui Wang, Josef Kittler
We propose a novel framework for representing image sets by approximating infinite-dimensional CovDs in the paradigm of the Nystr\"om method based on a Riemannian kernel.
no code implementations • 30 May 2018 • Rui Wang, Xiao-Jun Wu, Kai-Xuan Chen, Josef Kittler
In image set classification, a considerable advance has been made by modeling the original image sets by second order statistics or linear subspace, which typically lie on the Riemannian manifold.
no code implementations • 27 May 2018 • Rui Wang, Xiao-Jun Wu, Josef Kittler
The proposed RieMNet and DRieMNet are evaluated on three tasks: video-based face recognition, set-based object categorization, and set-based cell identification.
no code implementations • 26 May 2018 • YunKun Li, Xiao-Jun Wu, Josef Kittler
In our network, the role of L1-(2D)2PCA is to learn the filters of multiple convolution layers.
2 code implementations • 25 Apr 2018 • Hui Li, Xiao-Jun Wu, Tariq Durrani
Multi-focus noisy image fusion represents an important task in the field of image fusion which generates a single, clear and focused image from all source images.
2 code implementations • 24 Apr 2018 • Hui Li, Xiao-Jun Wu
Then, the low-rank parts are fused by weighted-average strategy to preserve more contour information.
2 code implementations • 23 Apr 2018 • Hui Li, Xiao-Jun Wu
In this paper, we propose a novel multi-focus image fusion method based on dictionary learning and LRR to get a better performance in both global and local structure.
4 code implementations • 23 Apr 2018 • Hui Li, Xiao-Jun Wu
In this paper, we present a novel deep learning architecture for infrared and visible images fusion problem.
3 code implementations • 19 Apr 2018 • Hui Li, Xiao-Jun Wu, Josef Kittler
Then the base parts are fused by weighted-averaging.
no code implementations • 14 Mar 2018 • Zhen-Hua Feng, Patrik Huber, Josef Kittler, Peter JB Hancock, Xiao-Jun Wu, Qijun Zhao, Paul Koppen, Matthias Rätsch
To this end, we organise a competition that provides a new benchmark dataset that contains 2000 2D facial images of 135 subjects as well as their 3D ground truth face scans.
6 code implementations • CVPR 2018 • Zhen-Hua Feng, Josef Kittler, Muhammad Awais, Patrik Huber, Xiao-Jun Wu
We present a new loss function, namely Wing loss, for robust facial landmark localisation with Convolutional Neural Networks (CNNs).
Ranked #1 on
Face Alignment
on 300W
(NME_inter-pupil (%, Common) metric)
no code implementations • 5 May 2017 • Zhen-Hua Feng, Josef Kittler, Muhammad Awais, Patrik Huber, Xiao-Jun Wu
The framework has four stages: face detection, bounding box aggregation, pose estimation and landmark localisation.
no code implementations • 30 Dec 2016 • Zhen-Hua Feng, Josef Kittler, William Christmas, Xiao-Jun Wu
To deal with this challenge, we present a Unified Tensor-based Active Appearance Model (UT-AAM) for jointly modelling the geometry and texture information of 2D faces.
no code implementations • CVPR 2017 • Zhen-Hua Feng, Josef Kittler, William Christmas, Patrik Huber, Xiao-Jun Wu
We present a new Cascaded Shape Regression (CSR) architecture, namely Dynamic Attention-Controlled CSR (DAC-CSR), for robust facial landmark detection on unconstrained faces.
Ranked #18 on
Face Alignment
on AFLW-19
no code implementations • 1 Nov 2016 • Xiaoning Song, Zhen-Hua Feng, Guosheng Hu, Josef Kittler, William Christmas, Xiao-Jun Wu
The paper presents a dictionary integration algorithm using 3D morphable face models (3DMM) for pose-invariant collaborative-representation-based face classification.
no code implementations • 12 Jun 2013 • Jun Sun, Xiao-Jun Wu, Vasile Palade, Wei Fang, Yuhui Shi
The free electron model considers that electrons have both a thermal and a drift motion in a conductor that is placed in an external electric field.