Ye 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
Ye Li has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Guangqiang Yin
School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
8 shared publications - Zhiguo Wang
Center for Public Security Technology, University of Electronic Science and Technology of China, Chengdu, China
5 shared publications Shaoqi Hou
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
2 shared publications- Shaoqi Hou
Shenzhen Institute of Information Technology, Shenzhen, China
2 shared publications - Xiaoyu Yang
University of Electronic Science and Technology of China
2 shared publications - Yixi Pan
Glasgow College, University of Electronic Science and Technology of China, Chengdu, China
2 shared publications
Latest Publications
- 25 March 2024
- Published by Springer Nature in Computing
- Vol. 106 (5) , 1681-1705
Person re-identification method based on fine-grained feature fusion and self-attention mechanism
- 25 March 2024
- Published by Springer Nature in Computing
- Vol. 106 (5) , 1681-1705
Person re-identification method based on fine-grained feature fusion and self-attention mechanism
- 25 March 2024
- Published by Springer Nature in The Visual Computer
- Vol. 41 (1) , 437-449
Multi-keypoints matching network for clothing detection
- 25 March 2024
- Published by Springer Nature in The Visual Computer
- Vol. 41 (1) , 437-449
Multi-keypoints matching network for clothing detection
- 2 February 2024
- Published by Springer Nature
- p. 355-365
Mutual Learning Person Search Based on Region Alignment
- 2 February 2024
- Published by Springer Nature
- p. 355-365
Mutual Learning Person Search Based on Region Alignment
- 6 December 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (18) , 56077-56101
Cross-domain person re-identification with normalized and enhanced feature
- 6 December 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (18) , 56077-56101
Cross-domain person re-identification with normalized and enhanced feature
- 24 November 2023
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (9) , 11823-11844
Joint Detection and Association for End-to-End Multi-object Tracking
- 24 November 2023
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (9) , 11823-11844
Joint Detection and Association for End-to-End Multi-object Tracking
- 9 September 2021
- Published by Springer Nature
- p. 58-69
SAPN: Spatial Attention Pyramid Network for Cross-Domain Person Re-Identification
- 9 September 2021
- Published by Springer Nature
- p. 58-69
SAPN: Spatial Attention Pyramid Network for Cross-Domain Person Re-Identification
- Open Access
- 1 January 2021
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2021 (1)
Hybrid Pyramid Convolutional Network for Multiscale Face Detection
Face detection remains a challenging problem due to the high variability of scale and occlusion despite the strong representational power of deep convolutional neural networks and their implicit robustness. To handle hard face detection under extreme circumstances especially tiny faces detection, in this paper, we proposed a multiscale Hybrid Pyramid Convolutional Network (HPCNet), which is a one‐stage fully convolutional network. Our HPCNet consists of three newly presented modules: firstly, we designed the Hybrid Dilated Convolution (HDC) module to replace the fully connected layers in VGG16, which enlarges receptive field and reduces its loss of local information; secondly, we constructed the Hybrid Feature Pyramid (HFP) to combine semantic information from higher layers together with details from lower layers; and thirdly, to deal with the problem of occlusion and blurring effectively, we introduced Context Information Extractor (CIE) in HPCNet. In addition, we presented an improved Online Hard Example Mining (OHEM) strategy, which can enhance the average precision of face detection by balancing the number of positive and negative samples. Our method has achieved an accuracy of 0.933, 0.924, and 0.848 on the Easy, Medium, and Hard subset of WIDER FACE, respectively, which surpasses most of the advanced algorithms.
- 1 January 2021
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2021 (1)
Open AccessHybrid Pyramid Convolutional Network for Multiscale Face Detection
Face detection remains a challenging problem due to the high variability of scale and occlusion despite the strong representational power of deep convolutional neural networks and their implicit robustness. To handle hard face detection under extreme circumstances especially tiny faces detection, in this paper, we proposed a multiscale Hybrid Pyramid Convolutional Network (HPCNet), which is a one‐stage fully convolutional network. Our HPCNet consists of three newly presented modules: firstly, we designed the Hybrid Dilated Convolution (HDC) module to replace the fully connected layers in VGG16, which enlarges receptive field and reduces its loss of local information; secondly, we constructed the Hybrid Feature Pyramid (HFP) to combine semantic information from higher layers together with details from lower layers; and thirdly, to deal with the problem of occlusion and blurring effectively, we introduced Context Information Extractor (CIE) in HPCNet. In addition, we presented an improved Online Hard Example Mining (OHEM) strategy, which can enhance the average precision of face detection by balancing the number of positive and negative samples. Our method has achieved an accuracy of 0.933, 0.924, and 0.848 on the Easy, Medium, and Hard subset of WIDER FACE, respectively, which surpasses most of the advanced algorithms.
- Open Access
- 20 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 164570-164579
Feature Pyramid Attention Model and Multi-Label Focal Loss for Pedestrian Attribute Recognition
At present, there are many challenges in the field of pedestrian attribute recognition, such as small targets of some attributes, imbalanced samples, and low recognition accuracy of complex samples. In view of the above problems, we improved the model in two perspectives: 1) We proposed Feature Pyramid Attention Model (FPAM). In order to solve the problem that attributes are distributed in different locations in the pedestrian image, FPAM adopted the attention mechanism on the basis of ResNet-50, by which the model’s attention could be focused on key areas of the image. As for the difficulty in small targets attributes, we adopted feature pyramid integration strategy; 2) We proposed Multi Label Focal Loss (MLFL). Referring to Binary Cross Entropy Loss Function (CE) and Weight Binary Cross Entropy Loss Function (WCE), we added the weight parameters of samples which are difficult to classify to improve the recognition accuracy, and the rate of convergence was increased. Results show that our proposed method achieves 84.83% mA, 79.37% Accuracy, 87.47% Precision, 86.09% Recall, and 86.77% F1 on PETA dataset.
- 20 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 164570-164579
Open AccessFeature Pyramid Attention Model and Multi-Label Focal Loss for Pedestrian Attribute Recognition
At present, there are many challenges in the field of pedestrian attribute recognition, such as small targets of some attributes, imbalanced samples, and low recognition accuracy of complex samples. In view of the above problems, we improved the model in two perspectives: 1) We proposed Feature Pyramid Attention Model (FPAM). In order to solve the problem that attributes are distributed in different locations in the pedestrian image, FPAM adopted the attention mechanism on the basis of ResNet-50, by which the model’s attention could be focused on key areas of the image. As for the difficulty in small targets attributes, we adopted feature pyramid integration strategy; 2) We proposed Multi Label Focal Loss (MLFL). Referring to Binary Cross Entropy Loss Function (CE) and Weight Binary Cross Entropy Loss Function (WCE), we added the weight parameters of samples which are difficult to classify to improve the recognition accuracy, and the rate of convergence was increased. Results show that our proposed method achieves 84.83% mA, 79.37% Accuracy, 87.47% Precision, 86.09% Recall, and 86.77% F1 on PETA dataset.
- Open Access
Triplet Online Instance Matching Loss for Person Re-identification
Mining the shared features of same identity in different scene, and the unique features of different identity in same scene, are most significant challenges in the field of person re-identification (ReID). Online Instance Matching (OIM) loss function and Triplet loss function are main methods for person ReID. Unfortunately, both of them have drawbacks. OIM loss treats all samples equally and puts no emphasis on hard samples. Triplet loss processes batch construction in a complicated and fussy way and converges slowly. For these problems, we propose a Triplet Online Instance Matching (TOIM) loss function, which lays emphasis on the hard samples and improves the accuracy of person ReID effectively. It combines the advantages of OIM loss and Triplet loss and simplifies the process of batch construction, which leads to a more rapid convergence. It can be trained on-line when handle the joint detection and identification task. To validate our loss function, we collect and annotate a large-scale benchmark dataset (UESTC-PR) based on images taken from surveillance cameras, which contains 499 identities and 60,437 images. We evaluated our proposed loss function on Duke, Marker-1501 and UESTC-PR using ResNet-50, and the result shows that our proposed loss function outperforms the baseline methods by a maximum of 21.7%, including Softmax loss, OIM loss and Triplet loss.
Open AccessTriplet Online Instance Matching Loss for Person Re-identification
Mining the shared features of same identity in different scene, and the unique features of different identity in same scene, are most significant challenges in the field of person re-identification (ReID). Online Instance Matching (OIM) loss function and Triplet loss function are main methods for person ReID. Unfortunately, both of them have drawbacks. OIM loss treats all samples equally and puts no emphasis on hard samples. Triplet loss processes batch construction in a complicated and fussy way and converges slowly. For these problems, we propose a Triplet Online Instance Matching (TOIM) loss function, which lays emphasis on the hard samples and improves the accuracy of person ReID effectively. It combines the advantages of OIM loss and Triplet loss and simplifies the process of batch construction, which leads to a more rapid convergence. It can be trained on-line when handle the joint detection and identification task. To validate our loss function, we collect and annotate a large-scale benchmark dataset (UESTC-PR) based on images taken from surveillance cameras, which contains 499 identities and 60,437 images. We evaluated our proposed loss function on Duke, Marker-1501 and UESTC-PR using ResNet-50, and the result shows that our proposed loss function outperforms the baseline methods by a maximum of 21.7%, including Softmax loss, OIM loss and Triplet loss.
- Open Access
- 10 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 30682-30691
A Face Detection Algorithm Based on Two Information Flow Block and Retinal Receptive Field Block
- 10 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 30682-30691
Open AccessA Face Detection Algorithm Based on Two Information Flow Block and Retinal Receptive Field Block