no code implementations • 29 Sep 2020 • Zhiyuan Zhao, Tao Han, Junyu. Gao, Qi. Wang, Xuelong. Li
Drones shooting can be applied in dynamic traffic monitoring, object detecting and tracking, and other vision tasks.
no code implementations • 10 Mar 2020 • Rui Zhang, Yunxing Zhang, Xuelong. Li
Moreover, the adjacency matrix can be self-learned for better embedding performance when the original graph structure is incomplete.
1 code implementation • 6 Mar 2020 • Wei. Lin, Junyu. Gao, Qi. Wang, Xuelong. Li
Recently, lots of deep networks are proposed to improve the quality of predicted super-resolution (SR) images, due to its widespread use in several image-based fields.
1 code implementation • 20 Feb 2020 • Xuelong. Li, Hongyuan Zhang, Rui Zhang
Therefore, how to extend graph convolution networks into general clustering tasks is an attractive problem.
no code implementations • 14 Jan 2020 • Qi. Wang, Qiang Li, Xuelong. Li
Deep learning-based hyperspectral image super-resolution (SR) methods have achieved great success recently.
4 code implementations • 10 Jan 2020 • Qi. Wang, Junyu. Gao, Wei. Lin, Xuelong. Li
In the last decade, crowd counting and localization attract much attention of researchers due to its wide-spread applications, including crowd monitoring, public safety, space design, etc.
no code implementations • 19 Aug 2019 • Jinglin Xu, Junwei Han, Mingliang Xu, Feiping Nie, Xuelong. Li
Clustering is an effective technique in data mining to group a set of objects in terms of some attributes.
no code implementations • 29 Jul 2019 • Xuelong. Li, Hongli Li, Yongsheng Dong
Particularly, MetaL-TDVS aims to excavate the latent mechanism for summarizing video by reformulating video summarization as a meta learning problem and promote generalization ability of the trained model.
no code implementations • 2 Jul 2019 • Feiping Nie, Zhanxuan Hu, Xiaoqian Wang, Rong Wang, Xuelong. Li, Heng Huang
This work aims at solving the problems with intractable sparsity-inducing norms that are often encountered in various machine learning tasks, such as multi-task learning, subspace clustering, feature selection, robust principal component analysis, and so on.
no code implementations • 21 Jun 2019 • Feiping Nie, Jing Li, Xuelong. Li
Exploiting different representations, or views, of the same object for better clustering has become very popular these days, which is conventionally called multi-view clustering.
no code implementations • 29 May 2019 • Xuelong. Li, Aihong Yuan, Xiaoqiang Lu
To make full use of these information, this paper attempt to exploit the text guided attention and semantic-guided attention (SA) to find the more correlated spatial information and reduce the semantic gap between vision and language.
1 code implementation • 24 May 2019 • Junyu. Gao, Qi. Wang, Xuelong. Li
Crowd counting from a single image is a challenging task due to high appearance similarity, perspective changes and severe congestion.
no code implementations • 7 May 2019 • Qi. Wang, Xiange He, Xuelong. Li
In this paper, a novel locality and structure regularized low rank representation (LSLRR) model is proposed for HSI classification.
1 code implementation • 5 May 2019 • Qi. Wang, Senior Member, Zhenghang Yuan, Qian Du, Xuelong. Li, Fellow, IEEE
In order to better handle high dimension problem and explore abundance information, this paper presents a General End-to-end Two-dimensional CNN (GETNET) framework for hyperspectral image change detection (HSI-CD).
no code implementations • 30 Apr 2019 • Qi. Wang, Fahong Zhang, Xuelong. Li
Band selection, by choosing a set of representative bands in hyperspectral image (HSI), is an effective method to reduce the redundant information without compromising the original contents.
no code implementations • 28 Apr 2019 • Xuelong. Li, Quanmao Lu, Yongsheng Dong, DaCheng Tao
This is due to that the CLF's influence function has a upper bound which can alleviate the influence of a single sample, especially the sample with a large noise, on estimating the residuals.
no code implementations • 28 Apr 2019 • Bin Zhao, Xuelong. Li, Xiaoqiang Lu
Compared to traditional RNNs, H-RNN is more suitable to video summarization, since it can exploit long temporal dependency among frames, meanwhile, the computation operations are significantly lessened.
no code implementations • 24 Apr 2019 • Xuelong. Li, Bin Zhao, Xiaoqiang Lu
Besides, the property-weights are learned for edited videos and raw videos, respectively.
no code implementations • 24 Apr 2019 • Bin Zhao, Xuelong. Li, Xiaoqiang Lu, Zhigang Wang
To address this problem, we make the first attempt to view weather recognition as a multi-label classification task, i. e., assigning an image more than one labels according to the displayed weather conditions.
no code implementations • 23 Apr 2019 • Lai Tian, Feiping Nie, Xuelong. Li
This paper presents new algorithms to solve the feature-sparsity constrained PCA problem (FSPCA), which performs feature selection and PCA simultaneously.
no code implementations • 21 Apr 2019 • Aihong Yuan, Xuelong. Li, Xiaoqiang Lu
In this paper, we propose a model with 3-gated model which fuses the global and local image features together for the task of image caption generation.
no code implementations • 20 Apr 2019 • Xuelong. Li, Aihong Yuan, Xiaoqiang Lu
And in the testing step, when an image is imported to our multi-modal GRU model, a sentence which describes the image content is generated.
no code implementations • CVPR 2019 • Di Hu, Dong Wang, Xuelong. Li, Feiping Nie, Qi. Wang
different encoding schemes indicate that using machine model to accelerate optimization evaluation and reduce experimental cost is feasible to some extent, which could dramatically promote the upgrading of encoding scheme then help the blind to improve their visual perception ability.
no code implementations • 19 Apr 2019 • Qi. Wang, Junyu. Gao, Xuelong. Li
In this paper, we propose a weakly supervised adversarial domain adaptation to improve the segmentation performance from synthetic data to real scenes, which consists of three deep neural networks.
no code implementations • 17 Apr 2019 • Xuelong. Li, Quanmao Lu, Yongsheng Dong, DaCheng Tao
Moreover, considering the importance of the discriminative information underlying in the initial clustering results, we add a discriminative constraint into our proposed objective function.
no code implementations • 16 Apr 2019 • Xuelong. Li, Kang Liu, Yongsheng Dong, DaCheng Tao
In this paper, a manifold matting framework named Patch Alignment Manifold Matting is proposed for image matting.
1 code implementation • 23 Jan 2019 • Shaohui Lin, Rongrong Ji, Yuchao Li, Cheng Deng, Xuelong. Li
In this paper, we propose a novel filter pruning scheme, termed structured sparsity regularization (SSR), to simultaneously speedup the computation and reduce the memory overhead of CNNs, which can be well supported by various off-the-shelf deep learning libraries.
no code implementations • 8 Oct 2018 • Di Hu, Feiping Nie, Xuelong. Li
The conventional supervised hashing methods based on classification do not entirely meet the requirements of hashing technique, but Linear Discriminant Analysis (LDA) does.
no code implementations • 8 Oct 2018 • Di Hu, Feiping Nie, Xuelong. Li
Hence, it is highly expected to learn effective joint representation by fusing the features of different modalities.
no code implementations • CVPR 2019 • Jiale Cao, Yanwei Pang, Xuelong. Li
Experimental results on the VOC2007 and VOC2012 datasets demonstrate that the proposed TripleNet is able to improve both the detection and segmentation accuracies without adding extra computational costs.
Ranked #18 on Semantic Segmentation on PASCAL VOC 2012 test
no code implementations • 4 Sep 2018 • Feiniu Yuan, Lin Zhang, Xue Xia, Boyang Wan, Qinghua Huang, Xuelong. Li
According to results of our deep segmentation method, we can easily and accurately perform smoke detection from videos.
no code implementations • 19 Aug 2018 • Pan Xiao, Bo Du, Jia Wu, Lefei Zhang, Ruimin Hu, Xuelong. Li
Many classic methods solve the domain adaptation problem by establishing a common latent space, which may cause the loss of many important properties across both domains.
1 code implementation • CVPR 2019 • Di Hu, Feiping Nie, Xuelong. Li
And such integrated multimodal clustering network can be effectively trained with max-margin loss in the end-to-end fashion.
no code implementations • CVPR 2018 • Bin Zhao, Xuelong. Li, Xiaoqiang Lu
Although video summarization has achieved great success in recent years, few approaches have realized the influence of video structure on the summarization results.
no code implementations • 3 Apr 2018 • Jiale Cao, Yanwei Pang, Xuelong. Li
In this paper, we propose a multi-branch and high-level semantic network by gradually splitting a base network into multiple different branches.
5 code implementations • 4 Jan 2018 • Dan Deng, Haifeng Liu, Xuelong. Li, Deng Cai
Most state-of-the-art scene text detection algorithms are deep learning based methods that depend on bounding box regression and perform at least two kinds of predictions: text/non-text classification and location regression.
Ranked #6 on Scene Text Detection on ICDAR 2013
2 code implementations • 21 Dec 2017 • Xiaoqiang Lu, Binqiang Wang, Xiangtao Zheng, Xuelong. Li
Finally, a comprehensive review is presented on the proposed data set to fully advance the task of remote sensing caption.
no code implementations • 31 Aug 2017 • Zhong Ji, Kailin Xiong, Yanwei Pang, Xuelong. Li
This paper addresses the problem of supervised video summarization by formulating it as a sequence-to-sequence learning problem, where the input is a sequence of original video frames, the output is a keyshot sequence.
Ranked #4 on Video Summarization on TvSum (using extra training data)
no code implementations • ICCV 2017 • Xuelong. Li, Di Hu, Xiaoqiang Lu
Image is usually taken for expressing some kinds of emotions or purposes, such as love, celebrating Christmas.
1 code implementation • 17 Aug 2017 • Xuelong. Li, Di Hu, Feiping Nie
Based on the analysis, we provide a so-called Deep Binary Reconstruction (DBRC) network that can directly learn the binary hashing codes in an unsupervised fashion.
no code implementations • 8 Aug 2017 • Jingkuan Song, Yuyu Guo, Lianli Gao, Xuelong. Li, Alan Hanjalic, Heng Tao Shen
In this paper, we propose a generative approach, referred to as multi-modal stochastic RNNs networks (MS-RNN), which models the uncertainty observed in the data using latent stochastic variables.
no code implementations • 13 Jul 2017 • Zhong Ji, Yaru Ma, Yanwei Pang, Xuelong. Li
Given the explosive growth of online videos, it is becoming increasingly important to relieve the tedious work of browsing and managing the video content of interest.
no code implementations • 28 Apr 2017 • Guanjun Guo, Hanzi Wang, Wan-Lei Zhao, Yan Yan, Xuelong. Li
Based on the new Cohesion Measurement, a novel object discovery method is proposed to discover objects latent in an image by utilizing the eigenvectors of the affinity matrix.
no code implementations • 15 Nov 2016 • Ping Li, Jun Yu, Meng Wang, Luming Zhang, Deng Cai, Xuelong. Li
To achieve this goal, we cast the problem into a constrained rank minimization framework by adopting the least squares regularization.
no code implementations • CVPR 2016 • Di Hu, Xuelong. Li, Xiaoqiang Lu
Recently, audiovisual speech recognition based the MRBM has attracted much attention, and the MRBM shows its effectiveness in learning the joint representation across audiovisual modalities.
no code implementations • 24 Apr 2016 • Dingwen Zhang, Huazhu Fu, Junwei Han, Ali Borji, Xuelong. Li
Co-saliency detection is a newly emerging and rapidly growing research area in computer vision community.
no code implementations • 22 Mar 2016 • Yanwei Pang, Manli Sun, Xiaoheng Jiang, Xuelong. Li
In this paper, we propose to replace dense shallow MLP with sparse shallow MLP.
no code implementations • 1 Mar 2016 • Jiale Cao, Yanwei Pang, Xuelong. Li
For example, CNN classifies these proposals by the full-connected layer features while proposal scores and the features in the inner-layers of CNN are ignored.
Ranked #25 on Pedestrian Detection on Caltech
no code implementations • 1 Mar 2016 • Xiaoheng Jiang, Yanwei Pang, Manli Sun, Xuelong. Li
The first one is a linear filter of spatial size $ h\times w $ and is aimed at extracting features from spatial domain.
no code implementations • 23 Feb 2016 • Zheng Zhang, Yong Xu, Jian Yang, Xuelong. Li, David Zhang
The main purpose of this article is to provide a comprehensive study and an updated review on sparse representation and to supply a guidance for researchers.
no code implementations • ICCV 2015 • Hongchang Gao, Feiping Nie, Xuelong. Li, Heng Huang
In this paper, we propose a novel multi-view subspace clustering method.
no code implementations • CVPR 2016 • Jiale Cao, Yanwei Pang, Xuelong. Li
Finally, we propose to combine both non-neighboring and neighboring features for pedestrian detection.
Ranked #28 on Pedestrian Detection on Caltech
no code implementations • 13 Nov 2015 • Tianshui Chen, Liang Lin, Lingbo Liu, Xiaonan Luo, Xuelong. Li
Our DISC framework is capable of uniformly highlighting the objects-of-interest from complex background while preserving well object details.
no code implementations • 30 Sep 2015 • Yanwei Pang, Li Ye, Xuelong. Li, Jing Pan
So there are undesirable false alarms and missed alarms in many algorithms of moving object detection.
no code implementations • 23 Aug 2015 • Yanwei Pang, Jiale Cao, Xuelong. Li
Multistage particle windows (MPW), proposed by Gualdi et al., is an algorithm of fast and accurate object detection.
no code implementations • 18 Aug 2015 • Yanwei Pang, Jiale Cao, Xuelong. Li
iCascade searches the optimal number ri of weak classifiers of each stage i by directly minimizing the computation cost of the cascade.
no code implementations • CVPR 2015 • Dihong Gong, Zhifeng Li, DaCheng Tao, Jianzhuang Liu, Xuelong. Li
In this paper, we propose a new approach to overcome the representation and matching problems in age invariant face recognition.
no code implementations • 4 Oct 2014 • Nannan Wang, Xinbo Gao, DaCheng Tao, Xuelong. Li
CLM-based methods consist of a shape model and a number of local experts, each of which is utilized to detect a facial feature point.
1 code implementation • IEEE Trans. on Image Processing 2014 • Jianbing Shen, Yunfan Du, Wenguan Wang, Xuelong. Li
Then, the boundaries of initial superpixels are obtained according to the probabilities and the commute time.
no code implementations • 1 Sep 2013 • Fei Gao, DaCheng Tao, Xinbo Gao, Xuelong. Li
The proposed BIQA method is one of learning to rank.
no code implementations • CVPR 2013 • Yue Lin, Rong Jin, Deng Cai, Shuicheng Yan, Xuelong. Li
Recent studies have shown that hashing methods are effective for high dimensional nearest neighbor search.