1 code implementation • ICML 2020 • Dejun Chu, Chang-Shui Zhang, Shiliang Sun, Qing Tao
Structured sparsity-inducing $\ell_{1, \infty}$-norm, as a generalization of the classical $\ell_1$-norm, plays an important role in jointly sparse models which select or remove simultaneously all the variables forming a group.
no code implementations • 4 Jul 2020 • Yiwen Guo, Long Chen, Yurong Chen, Chang-Shui Zhang
This paper analyzes regularization terms proposed recently for improving the adversarial robustness of deep neural networks (DNNs), from a theoretical point of view.
no code implementations • 24 Jun 2020 • Yiwen Sun, Kun fu, Zheng Wang, Chang-Shui Zhang, Jieping Ye
To address the data sparsity problem, we propose the Road Network Metric Learning framework for ETA (RNML-ETA).
1 code implementation • 15 Jun 2020 • Sen Cui, Weishen Pan, Chang-Shui Zhang, Fei Wang
Bipartite ranking, which aims to learn a scoring function that ranks positive individuals higher than negative ones from labeled data, is widely adopted in various applications where sample prioritization is needed.
no code implementations • 7 Jun 2020 • Yiwen Sun, Yulu Wang, Kun fu, Zheng Wang, Chang-Shui Zhang, Jieping Ye
Furthermore, in order to evaluate Fusion RNN's sequence feature extraction capability, we choose a representative data mining task for sequence data, estimated time of arrival (ETA) and present a novel model based on Fusion RNN.
no code implementations • 7 Jun 2020 • Yiwen Sun, Yulu Wang, Kun fu, Zheng Wang, Ziang Yan, Chang-Shui Zhang, Jieping Ye
Estimated time of arrival (ETA) is one of the most important services in intelligent transportation systems and becomes a challenging spatial-temporal (ST) data mining task in recent years.
1 code implementation • ICLR 2020 • Kailun Wu, Yiwen Guo, Ziang Li, Chang-Shui Zhang
In this paper, we study the learned iterative shrinkage thresholding algorithm (LISTA) for solving sparse coding problems.
no code implementations • 23 Apr 2020 • Yiwen Sun, Yulu Wang, Kun fu, Zheng Wang, Chang-Shui Zhang, Jieping Ye
Recently, deep learning based methods have achieved promising results by adopting graph convolutional network (GCN) to extract the spatial correlations and recurrent neural network (RNN) to capture the temporal dependencies.
1 code implementation • CVPR 2020 • Jinlin Liu, Yuan YAO, Wendi Hou, Miaomiao Cui, Xuansong Xie, Chang-Shui Zhang, Xian-Sheng Hua
In this paper, we propose to use coarse annotated data coupled with fine annotated data to boost end-to-end semantic human matting without trimaps as extra input.
Ranked #9 on Image Matting on AM-2K
no code implementations • CVPR 2020 • Shan You, Tao Huang, Mingmin Yang, Fei Wang, Chen Qian, Chang-Shui Zhang
The training efficiency is thus boosted since the training space has been greedily shrunk from all paths to those potentially-good ones.
Ranked #72 on Neural Architecture Search on ImageNet
no code implementations • 8 Feb 2020 • Nan Jiang, Sheng Jin, Zhiyao Duan, Chang-Shui Zhang
We cast this as a reinforcement learning problem, where the generation agent learns a policy to generate a musical note (action) based on previously generated context (state).
1 code implementation • 14 Nov 2019 • Ziang Yan, Yiwen Guo, Chang-Shui Zhang
The tremendous recent success of deep neural networks (DNNs) has sparked a surge of interest in understanding their predictive ability.
1 code implementation • IJCNLP 2019 • Xintong Yu, Hongming Zhang, Yangqiu Song, Yan Song, Chang-Shui Zhang
To tackle this challenge, in this paper, we formally define the task of visual-aware pronoun coreference resolution (PCR) and introduce VisPro, a large-scale dialogue PCR dataset, to investigate whether and how the visual information can help resolve pronouns in dialogues.
no code implementations • 23 Aug 2019 • Jiang Lu, Lei LI, Chang-Shui Zhang
Remarkable gains in deep learning usually rely on tremendous supervised data.
2 code implementations • NeurIPS 2019 • Ziang Yan, Yiwen Guo, Chang-Shui Zhang
Unlike the white-box counterparts that are widely studied and readily accessible, adversarial examples in black-box settings are generally more Herculean on account of the difficulty of estimating gradients.
no code implementations • 19 Apr 2019 • Yiwen Guo, Ming Lu, WangMeng Zuo, Chang-Shui Zhang, Yurong Chen
Convolutional neural networks have been proven effective in a variety of image restoration tasks.
1 code implementation • CVPR 2020 • Tianhong Li, Jianguo Li, Zhuang Liu, Chang-Shui Zhang
Deep neural network compression techniques such as pruning and weight tensor decomposition usually require fine-tuning to recover the prediction accuracy when the compression ratio is high.
1 code implementation • NeurIPS 2018 • Hu Liu, Sheng Jin, Chang-Shui Zhang
Connectionist Temporal Classification (CTC) is an objective function for end-to-end sequence learning, which adopts dynamic programming algorithms to directly learn the mapping between sequences.
no code implementations • NeurIPS 2018 • Yiwen Guo, Chao Zhang, Chang-Shui Zhang, Yurong Chen
Deep neural networks (DNNs) are computationally/memory-intensive and vulnerable to adversarial attacks, making them prohibitive in some real-world applications.
1 code implementation • 18 Sep 2018 • Jian Liang, Ziqi Liu, Jiayu Zhou, Xiaoqian Jiang, Chang-Shui Zhang, Fei Wang
Multi-task learning (MTL) refers to the paradigm of learning multiple related tasks together.
1 code implementation • NeurIPS 2018 • Ziang Yan, Yiwen Guo, Chang-Shui Zhang
Despite the efficacy on a variety of computer vision tasks, deep neural networks (DNNs) are vulnerable to adversarial attacks, limiting their applications in security-critical systems.
no code implementations • 24 Dec 2017 • Shiliang Sun, Chang-Shui Zhang, Yi Zhang
A novel predictor for traffic flow forecasting, namely spatio-temporal Bayesian network predictor, is proposed.
no code implementations • 26 Sep 2017 • Jiang Lu, Jie Hu, Guannan Zhao, Fenghua Mei, Chang-Shui Zhang
Crop diseases are responsible for the major production reduction and economic losses in agricultural industry world- wide.
12 code implementations • ICCV 2017 • Zhuang Liu, Jianguo Li, Zhiqiang Shen, Gao Huang, Shoumeng Yan, Chang-Shui Zhang
For VGGNet, a multi-pass version of network slimming gives a 20x reduction in model size and a 5x reduction in computing operations.
no code implementations • CVPR 2017 • Runpeng Cui, Hu Liu, Chang-Shui Zhang
This work presents a weakly supervised framework with deep neural networks for vision-based continuous sign language recognition, where the ordered gloss labels but no exact temporal locations are available with the video of sign sentence, and the amount of labeled sentences for training is limited.
no code implementations • 19 Mar 2017 • Jiang Lu, Jin Li, Ziang Yan, Chang-Shui Zhang
Given the dataset of seen classes and side information of unseen classes (e. g. attributes), we synthesize feature-level pseudo representations for novel concepts, which allows us access to the formulation of unseen class predictor.
no code implementations • 28 Feb 2017 • Ziang Yan, Jian Liang, Weishen Pan, Jin Li, Chang-Shui Zhang
Object detection when provided image-level labels instead of instance-level labels (i. e., bounding boxes) during training is an important problem in computer vision, since large scale image datasets with instance-level labels are extremely costly to obtain.
no code implementations • 14 Nov 2016 • Chengzhe Yan, Jie Hu, Chang-Shui Zhang
In this paper, a novel neural network architecture is proposed attempting to rectify text images with mild assumptions.
no code implementations • 1 Sep 2016 • Junqi Jin, Ziang Yan, Kun fu, Nan Jiang, Chang-Shui Zhang
Deep learning models' architectures, including depth and width, are key factors influencing models' performance, such as test accuracy and computation time.
no code implementations • 29 Aug 2016 • Junqi Jin, Ziang Yan, Kun fu, Nan Jiang, Chang-Shui Zhang
A greedy algorithm with bounds is suggested to solve the transformed problem.
1 code implementation • 20 Jun 2015 • Junqi Jin, Kun fu, Runpeng Cui, Fei Sha, Chang-Shui Zhang
In this paper, we propose an image caption system that exploits the parallel structures between images and sentences.
no code implementations • CVPR 2014 • Lyndsey C. Pickup, Zheng Pan, Donglai Wei, YiChang Shih, Chang-Shui Zhang, Andrew Zisserman, Bernhard Scholkopf, William T. Freeman
We explore whether we can observe Time's Arrow in a temporal sequence--is it possible to tell whether a video is running forwards or backwards?
no code implementations • 14 Jun 2013 • Zheng Pan, Chang-Shui Zhang
Finally, we perform some experiments to show the performance of CD methods on giving AGAS solutions and the degree of weakness of the estimation conditions required by the sharp concave regularizers.
4 code implementations • 18 Mar 2013 • Pinghua Gong, Chang-Shui Zhang, Zhaosong Lu, Jianhua Huang, Jieping Ye
A commonly used approach is the Multi-Stage (MS) convex relaxation (or DC programming), which relaxes the original non-convex problem to a sequence of convex problems.
no code implementations • 15 Jan 2013 • Zhen Hu, Kun fu, Chang-Shui Zhang
We think our method is promising even though we test it in a different data set, since our data set is comparable to that in MIREX by size.
no code implementations • NeurIPS 2012 • Pinghua Gong, Jieping Ye, Chang-Shui Zhang
In this paper, we propose a non-convex formulation for multi-task sparse feature learning based on a novel regularizer.
no code implementations • NeurIPS 2010 • Kun Gai, Guangyun Chen, Chang-Shui Zhang
Experiments show that our method significantly outperforms both SVM with the uniform combination of basis kernels and other state-of-art MKL approaches.