Haozhi Huang
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
Research Subjects
Haozhi Huang has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Di Wang
Jinan University, Zhuhai, China
2 shared publications - Guanghua Yang
School of Intelligent Systems Science and Engineering and the GBA and BR International Joint Research Center for Smart Logistics, Jinan University, Zhuhai, China
2 shared publications - Yanyan Liang
School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China
2 shared publications - Ajian Liu
Institute of Automation, Chinese Academy of Sciences, Beijing, China
1 shared publication - Haibin Zhu
Jinan University, Zhuhai, China
1 shared publication - Kun Cao
Jinan University, Zhuhai, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 175-184
VCAR: Training-Free 3DGS Segmentation via View Completeness and Axis-Aware Boundary Refinement
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 175-184
Open AccessVCAR: Training-Free 3DGS Segmentation via View Completeness and Axis-Aware Boundary Refinement
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33, 2974-2978
FS-DICP: A Fast and Simple Point-to-Point Iterative Closest Point Algorithm With Doppler Velocity
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33, 2974-2978
FS-DICP: A Fast and Simple Point-to-Point Iterative Closest Point Algorithm With Doppler Velocity
- Open Access
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 115-121
Fusing Asynchronous Event and Synchronization Frame Data with Multi-layer Feature Attention Guided Filtering
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 115-121
Open AccessFusing Asynchronous Event and Synchronization Frame Data with Multi-layer Feature Attention Guided Filtering
- 1 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Person Re-Identification via Feature Representation Learning Based on Verification Sample Constrain
In person re-identification (ReID) task, the variance between the samples are quite large, and there is no standard sample as a comparison. The current common method is to implement it as a classification task, which can get better results than the classical methods in verification task such as contrastive loss. However, the identification loss used in classification task only seeks the boundary of the classification, the intra-class distance between samples is still large so that it is insufficient for ReID task. In this paper, we consider to overcome these difficulties by proposing a joint loss with an identification loss and constrains of modeling the Euclidean distances between samples and their corresponding eigen data which is constructed by Principal Component Analysis method (PCA), we call it EigenPerson. The entire loss is formed in a linear combination. This work is mainly motivated by the center loss for face recognition problems, of which regularizations are restricted by a simultaneously learned center. We substitute the center with EigenPerson which we constructed offline as an auxiliary training sample. The learned model with our proposed method is evaluated on the benchmark of Market1501 and CUHK03 and achieve comparable results to those methods proposed in the same period.
- 1 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Person Re-Identification via Feature Representation Learning Based on Verification Sample Constrain
In person re-identification (ReID) task, the variance between the samples are quite large, and there is no standard sample as a comparison. The current common method is to implement it as a classification task, which can get better results than the classical methods in verification task such as contrastive loss. However, the identification loss used in classification task only seeks the boundary of the classification, the intra-class distance between samples is still large so that it is insufficient for ReID task. In this paper, we consider to overcome these difficulties by proposing a joint loss with an identification loss and constrains of modeling the Euclidean distances between samples and their corresponding eigen data which is constructed by Principal Component Analysis method (PCA), we call it EigenPerson. The entire loss is formed in a linear combination. This work is mainly motivated by the center loss for face recognition problems, of which regularizations are restricted by a simultaneously learned center. We substitute the center with EigenPerson which we constructed offline as an auxiliary training sample. The learned model with our proposed method is evaluated on the benchmark of Market1501 and CUHK03 and achieve comparable results to those methods proposed in the same period.
- 24 April 2019
- Published by Springer Nature
- p. 526-535
Constrainted Loss Function for Classification Problems
- 24 April 2019
- Published by Springer Nature
- p. 526-535
Constrainted Loss Function for Classification Problems
- Open Access
- 23 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 13643-13652
Learning Robust Embedding Representation With Hybrid Loss for Classification and Verification
This paper presents a method of building an embedding representation via deep metric learning, which works well in both classification and verification problems. The embedding is built via a proposed hybrid loss, which consists of a softmax loss and a Euclidean-metric loss. The hybrid loss explores the tradeoff balancing the discriminativeness and invariance. In deep metric learning, a softmax loss is proposed for classification and a Euclidean-metric loss is responsible for verification. We apply the proposed loss and the softmax loss to the well-known deep models, such as VGG-16 and ResNet-50, respectively. And the performances are evaluated by two datasets (CIFAR and Market1501), which the CIFAR is for classification and the Market1501 is for verification. The results indicate that the embedding learned from the proposed loss do improve the performance on both classification and verification tasks.
- 23 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 13643-13652
Open AccessLearning Robust Embedding Representation With Hybrid Loss for Classification and Verification
This paper presents a method of building an embedding representation via deep metric learning, which works well in both classification and verification problems. The embedding is built via a proposed hybrid loss, which consists of a softmax loss and a Euclidean-metric loss. The hybrid loss explores the tradeoff balancing the discriminativeness and invariance. In deep metric learning, a softmax loss is proposed for classification and a Euclidean-metric loss is responsible for verification. We apply the proposed loss and the softmax loss to the well-known deep models, such as VGG-16 and ResNet-50, respectively. And the performances are evaluated by two datasets (CIFAR and Market1501), which the CIFAR is for classification and the Market1501 is for verification. The results indicate that the embedding learned from the proposed loss do improve the performance on both classification and verification tasks.