Haiyun Guo, Female, Postgraduate Tutor

Foundation Model Research Center,  Institute of Automation Chinese Academy of Sciences

Selected to the young talent lifting project organized by Beijing Association for Science and Technology 


Mailing address:No.95 Zhongguancun East Road, Haidian District, Beijing, China

Postal code:100190

Research Areas

Image and Video Analysis

Multimodal content understanding

large-scale model training


2013.9-2018.6 University of Chinese Academy of Sciences, PhD

2009.9-2013.6 Wuhan University, Bachelor


Work Experience

2020.10-present, associate professor, institute of automation chinese academy of sciences

2018.7-2020.10, assistant professor, institute of automation chinese academy of sciences

Teaching Experience

2017-2020 Spring semester, Image and Video Retrieval (assistant teaching), postgraduate course for school of artificial intelligence, university of chinese academy of sciences


She has published 20 first-author or corresponding-author papers, including top journals like TIP, TNNLS, TITS and top conferences like AAAI, ECCV, CVPR, ACM MM etc. She has obtained around 20 invention patents authorization and participated in the formulation of 2 industry standards about vehicle feature recognition.

Some selected papers:

[1] Zhu Kuan, Guo Haiyun, Tang Ming, Wang Jinqiao. AAformer: Auto-Aligned Transformer for Person Re-Identification. IEEE Transactions on neural networks and learning system[J]. 2023.

[2] Li, Wei, Guo, Haiyun, Dong, Honghui, Tang, Ming, Zhou, Yue, Wang, Jinqiao. Bi-Level Implicit Semantic Data Augmentation for Vehicle Re-Identification. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS[J]. 2023.

[3] yongqi an, xu zhao, tao yu, Haiyun Guo, Chaoyang Zhao, ming tang, Jinqiao Wang. ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection. CVPR. 2023.

[4] Zhu Kuan, Guo Haiyun, Tang Ming, Wang Jinqiao. Learning semantics- consistent stripes with self-refinement for person re-identification. IEEE Transactions on neural networks and learning system[J]. 2022.

[5] Zhang, La, Guo, Haiyun, Zhu, Kuan, Qiao, Honglin, Huang, Gaopan, Zhang, Sen, Zhang, Huichen, Sun, Jian, Wang, Jinqiao. Hybrid Modality Metric Learning for Visible-Infrared Person Re-Identification. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS[J]. 2022, 18(1).

[6] Xu, Mingyuan, Guo, Haiyun, Jia, Yuheng, Dai, Zhitao, Wang, Jinqiao. Pseudo Label Rectification With Joint Camera Shift Adaptation and Outlier Progressive Recycling for Unsupervised Person Re-Identification. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS. 2022. 

[7] Zhu, Kuan, Guo, Haiyun, Yan, Tianyi, Zhu, Yousong, Wang, Jinqiao, Tang, Ming. PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification. ECCV. 2022.

[8] Tu Mingfei, Zhu Kuan, Guo Haiyun, Miao, Qinghai, Wang Jinqiao. Multi-granularity Mutual Learning Network for Object Re-identification. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS[J]. 2022.

[9] Liu, Songyan, Guo, Haiyun, Zhu, Kuan, Wang, Jinqiao, Tang, Ming. Unsupervised cycle-consistent person pose transfer. NEUROCOMPUTING[J]. 2021, 453: 502-511.

[10] Wen Xin, Li Biying, Guo Haiyun, Tang Ming, Wang Jinqiao. Adaptive Variance Based Label Distribution Learning For Facial Age Estimation. ECCV. 2020.

[11] Liu, Songyan, Guo, Haiyun, Hu, JianGuo, Zhao, Xu, Zhao, Chaoyang, Wang, Tong, Zhu, Yousong, Wang, Jinqiao, Tang, Ming. A novel data augmentation scheme for pedestrian detection with attribute preserving GAN. NEUROCOMPUTING[J]. 2020, 401(11): 123-132.

[12] Zhu Kuan, Guo Haiyun, Tang Ming, Wang Jinqiao. Identity-Guided Human Semantic Parsing for Person Re-Identification. ECCV. 2020.

[13] Guo, Haiyun, Zhu, Kuan, Tang, Ming, Wang, Jinqiao. Two-Level Attention Network With Multi-Grain Ranking Loss for Vehicle Re-Identification. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2019, 28(9): 4328-4338.

[14] Zhu, Yousong, Zhao, Chaoyang, Gun, Haiyun, Wang, Jinqiao, Zhao, Xu, Lu, Hanqing. Attention CoupleNet: Fully Convolutional Attention Coupling Network for Object Detection. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2019, 28(1): 113-126.

[15] Guo, Haiyun, Wu, Huiyao, Zhao, Chaoyang, Zhang, Huichen, Wang, Jinqiao, Lu, Hanqing. Cascade Attention Network for Person Re-Identification. 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP). 2019.

[16] Zhao, Xu, Zhao, Chaoyang, Guo, Haiyun, Zhu, Yousong, Tang, Ming, Wang, Jinqiao. Elite Loss for scene text detection. NEUROCOMPUTING[J]. 2019, 333(333): 284-291.

[17] Guo Haiyun, Zhao Chaoyang, Liu Zhiwei, Wang Jinqiao, Lu Hanqing. Learning Coarse-to-fine Structured Feature Embedding for Vehicle Re-identification. AAAI. 2018.

[18] Guo, Haiyun, Wang, Jinqiao, Gao, Yue, Li, Jianqiang, Lu, Hanqing. Multi-View 3D Object Retrieval With Deep Embedding Network. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2016, 25(12): 5526-5537.

[19] Guo Haiyun, Wang Jinqiao, Lu Hanqing. Learning Deep Compact Descriptor with Bagging Auto-encoders for Object Retrieval. ICIP. 2015.

[20] Guo Haiyun, Wang Jinqiao, Xu Min, Zha ZhengJun, Lu Hanqing. Learning Multi-view Deep Features for Small Object Retrieval in Surveillance Scenarios. ACM MM. 2015, 859-862.

Honors & Distinctions

1. 2022, Selected to the young talent lifting project organized by Beijing Association of Science and Technology.

2. 2020, Invention and Innovation silver award presented by China Association of Inventions.

3. 2019, Second prize for transformation for scientific and technological achievements presented by Chinese Academy of Sciences.

4. 2019, Winner of vehicle re-identification competition held during IEEE VCIP conference.

5. 2018, Second prize for Wu Wenjun Artificial Intelligence Science and Technology Award.

6. 2018, CAS-Rokid AI award.

7. 2015, Winner of multi-view 3D object retrieval competition held during Eurographics conference.

8. 2015, Second prize for cross-camera object tracking track of National Graduate Smart City Video Analysis Challenge.

Research Project

(1) Native full-stack extra large-scale model training technology, project lead, National project, 2021.12-2024.12

(2) Key technology for cross-media intelligent understanding software development, project lead, Guangdong project, 2020.1-2022.12

(3) Research and verification of parallel intelligence theory based on hybrid augmented intelligence, project lead, Guangdong project, 2020.1-2022.12

(4) Research on object retrieval of surveillance video based on adversarial learning and relational modeling, project lead, National project, 2021.1-2023.12

(5) Research on robust multi-granularity vehicle re-identification technology for intelligent highway scenes, project lead, Alibaba Innovative Research,2020.11-2022.11