Personal profile
Biography
Dr. Yuankai Qi joined the School of Computing at Macquarie University, Sydney, Australia, in December 2023 as a Lecturer (Assistant Professor) in Artificial Intelligence (AI). He is also an Adjunct Lecturer with the Australian Institute for Machine Learning (AIML) of The University of Adelaide. He received his PhD from Harbin Institute of Technology, China, during which he focused on the topic of visual object tracking. He was the winner of the international challenge on video segmentation and tracking DAVIS 2017, the Runner-up of the drone’s view object tracking challenge VisDrone 2018. In 2020, he received the CAAI Outstanding Doctoral Dissertations Award (10 winners each year across China).
Before joining Macquarie University, he was a Research Fellow at the Australian Institute for Machine Learning, University of Adelaide, working on vision-and-language navigation for robots. He has published over 60 papers on top-tier venues in computer vision and artificial intelligence, such as CVPR, NeurIPS, ICCV, ECCV, AAAI, IJCAI, IEEE TPAMI, and TIP. He received ACM Multimedia 2024 Best Paper Award, ICPR 2024 Best Student Paper Award, the Australian Pattern Recognition Society (APRS) ECR Award Honourable Mention in 2023.
Services:
- Area Chair for ICML 2026, CVPR 2026, AAAI 2026, ICLR 2026/2025, NeurIPS 2025, ICCV 2025.
- Regular reviewer for several prestigious conferences and journals, including CVPR, ICCV, AAAI, IJCAI, ICML, ACL, TPAMI, TIP, and PR.
Research topics:
- Vision-and-Language for Robot Action
- Video Captioning
- Medical Image Processing
- Crowd Counting
- Multi-view Clustering
- Video Anomaly Detection
- Federated Learning
- Movie Dubbing
- Visual Object Tracking
He has been recognised among the Stanford/Elsevier Top 2% Scientists globally in 2024 and 2025.
He is looking for self-motivated HDR students.
Teaching
COMP 3420 AI for Text and Vision
COMP 2250 Data Communication
Fingerprint
- 1 Similar Profiles
Collaborations and top research areas from the last five years
-
Next-Gen Banking: Towards Customized and Personalized Banking Solutions through Generative AI Technologies
Beheshti, A. (Primary Chief Investigator), Wu, J. (Chief Investigator), Zhang, X. (Chief Investigator), Qi, Y. (Chief Investigator), Xue, E. (Chief Investigator) & Alinejad Rokny, H. (Chief Investigator)
1/07/24 → 30/06/28
Project: Research
-
Establishing a Machine Learning Pipeline to Automate Tumor Segmentation from Written Radiology Report Data
Qi, Y. (Primary Chief Investigator), White, S. (Chief Investigator), Barras , C. (Supervisor), Phan, V. M. H. (Chief Investigator) & To, M.-S. (Chief Investigator)
1/01/25 → 31/12/25
Project: Research
-
AI-Enhanced CT Image Analysis for Precise Measurement of Bone Union and Healing in Jaw Reconstruction
Beheshti, A. (Primary Chief Investigator), Clarke AM, J. (Partner Investigator), Mukherjee, P. (Chief Investigator), Qi, Y. (Chief Investigator) & Gupta, V. (Chief Investigator)
1/10/24 → 31/12/25
Project: Research
Research Outputs
-
Dynamic example network for class-agnostic object counting
Liu, X., Li, G., Qi, Y., Yan, Z., Zhang, W., Qing, L. & Huang, Q., Feb 2026, In: Pattern Recognition. 170, p. 1-12 12 p., 111998.Research output: Contribution to journal › Article › peer-review
3 Link opens in a new tab Citations (Scopus) -
Ghost-free HDR imaging via latent low-frequency priors and deformable attention alignment
Hu, T., Yan, Q., Jin, J., Dong, W., Wu, P., Qi, Y., Lin, W. & Zhang, Y., 2026, In: IEEE Transactions on Image Processing. 35, p. 2684-2698 15 p.Research output: Contribution to journal › Article › peer-review
-
Indoor scene recognition in vision-and-language navigation
Zhang, H., Qi, Y., Zhao, M. & Liu, Y., Feb 2026, In: IEEE Transactions on Consumer Electronics. 72, 1, p. 1216-1222 7 p.Research output: Contribution to journal › Article › peer-review
-
Parameter-efficient action planning with large language models for vision-and-language navigation
Mohammadi, B., Abbasnejad, E., Qi, Y., Wu, Q., Van Den Hengel, A. & Shi, J. Q., Apr 2026, In: Pattern Recognition. 172, Part B, p. 1-11 11 p., 112462.Research output: Contribution to journal › Article › peer-review
Open AccessFile4 Link opens in a new tab Citations (Scopus)1 Downloads (Pure) -
RETTA: Retrieval-enhanced test-time adaptation for zero-shot video captioning
Ma, Y., Qing, L., Li, G., Qi, Y., Beheshti, A., Sheng, Q. Z. & Huang, Q., Mar 2026, In: Pattern Recognition. 171, Part A, p. 1-10 10 p., 112170.Research output: Contribution to journal › Article › peer-review
Open AccessFile7 Link opens in a new tab Citations (Scopus)1 Downloads (Pure)
Prizes
-
ACM Multimedia 2024 Best Paper Award
Zhang, Z. (Recipient), Li, L. (Recipient), Cong, G. (Recipient), Yin, H. (Recipient), Gao, Y. (Recipient), Yan, C. (Recipient), Van Den Hengel, A. (Recipient) & Qi, Y. (Recipient), 2024
Prize
-
-
-
ICPR 2024 Best Student Paper Award
Zhang, Z. (Recipient), Li, L. (Recipient), Zhang, J. (Recipient), Hu, Z. (Recipient), Wang, H. (Recipient), Yan, C. (Recipient), Yang, J. (Recipient) & Qi, Y. (Recipient), 2024
Prize
-