Jiawei Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jiawei Li has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Pong Chi Yuen
Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong
3 shared publications - Liang Zheng
Australian National University
2 shared publications - Mang Ye
Wuhan University, Wuhan, China
2 shared publications - Andy J Ma
Hong Kong Baptist University
1 shared publication Andy J. Ma
School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China
1 shared publication- Andy Jinhua Ma
School of Computer Science and Technology, Sun Yat-sen University, Guangzhou, China
1 shared publication
Latest Publications
- 14 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 28 (6) , 2976-2990
Dynamic Graph Co-Matching for Unsupervised Video-Based Person Re-Identification
Cross-camera label estimation from a set of unlabeled training data is an extremely important component in the unsupervised person re-identification (re-ID) systems. With the estimated labels, the existing advanced supervised learning methods can be leveraged to learn discriminative re-ID models. In this paper, we utilize the graph matching technique for accurate label estimation due to its advantages in optimal global matching and intra-camera relationship mining. However, the graph structure constructed with non-learned similarity measurement cannot handle the large cross-camera variations, which leads to noisy and inaccurate label outputs. This paper designs a dynamic graph matching (DGM) framework, which improves the label estimation process by iteratively refining the graph structure with better similarity measurement learned from the intermediate estimated labels. In addition, we design a positive re-weighting strategy to refine the intermediate labels, which enhances the robustness against inaccurate matching output and noisy initial training data. To fully utilize the abundant video information and reduce false matchings, a co-matching strategy is further incorporated into the framework. Comprehensive experiments conducted on three video benchmarks demonstrate that DGM outperforms the state-of-the-art unsupervised re-ID methods and yields the competitive performance to fully supervised upper bounds.
- 14 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 28 (6) , 2976-2990
Dynamic Graph Co-Matching for Unsupervised Video-Based Person Re-Identification
Cross-camera label estimation from a set of unlabeled training data is an extremely important component in the unsupervised person re-identification (re-ID) systems. With the estimated labels, the existing advanced supervised learning methods can be leveraged to learn discriminative re-ID models. In this paper, we utilize the graph matching technique for accurate label estimation due to its advantages in optimal global matching and intra-camera relationship mining. However, the graph structure constructed with non-learned similarity measurement cannot handle the large cross-camera variations, which leads to noisy and inaccurate label outputs. This paper designs a dynamic graph matching (DGM) framework, which improves the label estimation process by iteratively refining the graph structure with better similarity measurement learned from the intermediate estimated labels. In addition, we design a positive re-weighting strategy to refine the intermediate labels, which enhances the robustness against inaccurate matching output and noisy initial training data. To fully utilize the abundant video information and reduce false matchings, a co-matching strategy is further incorporated into the framework. Comprehensive experiments conducted on three video benchmarks demonstrate that DGM outperforms the state-of-the-art unsupervised re-ID methods and yields the competitive performance to fully supervised upper bounds.
- Open Access
- 1 January 2019
- Published by University of Wyoming Libraries in The Electronic Journal of Linear Algebra
- Vol. 35 (1) , 633-643
Inequalities for permanents and permanental minors of row substochastic matrices
In this paper, some inequalities for permanents and permanental minors of row substochastic matrices are proved. The convexity of the permanent function on the interval between the identity matrix and an arbitrary row substochastic matrix is also proved. In addition, a conjecture about the permanent and permanental minors of square row substochastic matrices with fixed row and column sums is formulated.
- 1 January 2019
- Published by University of Wyoming Libraries in The Electronic Journal of Linear Algebra
- Vol. 35 (1) , 633-643
Open AccessInequalities for permanents and permanental minors of row substochastic matrices
In this paper, some inequalities for permanents and permanental minors of row substochastic matrices are proved. The convexity of the permanent function on the interval between the identity matrix and an arbitrary row substochastic matrix is also proved. In addition, a conjecture about the permanent and permanental minors of square row substochastic matrices with fixed row and column sums is formulated.
- 27 March 2018
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 126 (8) , 855-874
Semi-supervised Region Metric Learning for Person Re-identification
- 27 March 2018
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 126 (8) , 855-874
Semi-supervised Region Metric Learning for Person Re-identification
- Open Access
Dynamic Label Graph Matching for Unsupervised Video Re-Identification
Label estimation is an important component in an unsupervised person re-identification (re-ID) system. This paper focuses on cross-camera label estimation, which can be subsequently used in feature learning to learn robust re-ID models. Specifically, we propose to construct a graph for samples in each camera, and then graph matching scheme is introduced for cross-camera labeling association. While labels directly output from existing graph matching methods may be noisy and inaccurate due to significant cross-camera variations, this paper proposes a dynamic graph matching (DGM) method. DGM iteratively updates the image graph and the label estimation process by learning a better feature space with intermediate estimated labels. DGM is advantageous in two aspects: 1) the accuracy of estimated labels is improved significantly with the iterations; 2) DGM is robust to noisy initial training data. Extensive experiments conducted on three benchmarks including the large-scale MARS dataset show that DGM yields competitive performance to fully supervised baselines, and outperforms competing unsupervised learning methods.
Open AccessDynamic Label Graph Matching for Unsupervised Video Re-Identification
Label estimation is an important component in an unsupervised person re-identification (re-ID) system. This paper focuses on cross-camera label estimation, which can be subsequently used in feature learning to learn robust re-ID models. Specifically, we propose to construct a graph for samples in each camera, and then graph matching scheme is introduced for cross-camera labeling association. While labels directly output from existing graph matching methods may be noisy and inaccurate due to significant cross-camera variations, this paper proposes a dynamic graph matching (DGM) method. DGM iteratively updates the image graph and the label estimation process by learning a better feature space with intermediate estimated labels. DGM is advantageous in two aspects: 1) the accuracy of estimated labels is improved significantly with the iterations; 2) DGM is robust to noisy initial training data. Extensive experiments conducted on three benchmarks including the large-scale MARS dataset show that DGM yields competitive performance to fully supervised baselines, and outperforms competing unsupervised learning methods.
- 1 December 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1313-1317
Facial Expression Recognition Based on Rotation Invariant Local Phase Quantization and Sparse Representation
In this paper, we propose a new algorithm for facial expression recognition (FER) based on rotation invariant Local Phase Quantization (RI-LPQ) and sparse representation. Firstly, Expression features are extracted using RI-LPQ descriptor. Then, Sparse Representation-based Classification (SRC) method is used to represent the test expression image by the linear combination of the training expression images. Facial expressions are discriminated by the residue analysis of sparse representation. The proposed method is experimented on Japanese Female Facial Expression (JAFFE) database. The new algorithms are assessed in comparison with the well known algorithms such as 2DPCA+SVM, LDA+SVM etc. The results illustrate that the proposed method has better performance than those traditional algorithms. In addition, in the case of expression images with different occlusion, recognition rate of the proposed method also gets better result.
- 1 December 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1313-1317
Facial Expression Recognition Based on Rotation Invariant Local Phase Quantization and Sparse Representation
In this paper, we propose a new algorithm for facial expression recognition (FER) based on rotation invariant Local Phase Quantization (RI-LPQ) and sparse representation. Firstly, Expression features are extracted using RI-LPQ descriptor. Then, Sparse Representation-based Classification (SRC) method is used to represent the test expression image by the linear combination of the training expression images. Facial expressions are discriminated by the residue analysis of sparse representation. The proposed method is experimented on Japanese Female Facial Expression (JAFFE) database. The new algorithms are assessed in comparison with the well known algorithms such as 2DPCA+SVM, LDA+SVM etc. The results illustrate that the proposed method has better performance than those traditional algorithms. In addition, in the case of expression images with different occlusion, recognition rate of the proposed method also gets better result.
- 27 November 2002
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 282-286
Obstacle avoidance using fuzzy neural networks
- 27 November 2002
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 282-286
Obstacle avoidance using fuzzy neural networks