Hengshuang Zhao

Assistant Professor
Department of Computer Science
The University of Hong Kong
Researcher, CSAIL, MIT
Email: hszhao[at]cs.hku.hk
or hszhao[at]csail.mit.edu


I am building a research group at the Department of Computer Science at The University of Hong Kong as an Assistant Professor. I am looking for self-motivated PhD/Postdoc/RA to join my group in Fall 2022, working together on exciting and cutting-edge computer vision, machine learning and artificial intelligence projects. Also, I am currently a postdoc researcher at Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT, working with Prof. Antonio Torralba.

Previously, I have spent wonderful times as a postdoctoral researcher at Torr Vision Group in the Department of Engineering Science at the University of Oxford (beautiful Oxford), working with Prof. Philip Torr. I obtained my Ph.D. degree in the Department of Computer Science and Engineering at The Chinese University of Hong Kong, supervised by Prof. Jiaya Jia. During Ph.D., I have spent wonderful times as an intern with Dr. Xiaohui Shen, Dr. Zhe Lin, Dr. Kalyan Sunkavalli, Dr. Brian Price at Adobe (San Jose), Prof. Raquel Urtasun at Uber (Toronto), and Dr. Vladlen Koltun at Intel (Santa Clara).

My general research interests cover the broad area of computer vision, machine learning and artificial intelligence, with special emphasis on building intelligent visual systems. My research goal is to utilize artificial intelligence techniques to make machines perceive, understand and interact with the surrounding environment, and ultimately make high positive impacts on various fields.

Several specific topics of our current research interests and focus: 1. image/video recognition like classification, segmentation, and detection; 2. 3d point cloud processing, scene reconstruction, and manipulation; 3. representation learning, unsupervised learning, weakly-/semi-supervised learning; 4. open-world learning, transfer learning, unified systems, advanced architecture design; 5. autonomous driving, multi-modal learning, vision+language, pretraining; 6. embodied ai, social navigation, interactive navigation, robot learning, etc.

Multiple openings for self-motivated PhD, Postdoc, RA and Interns! The current round for PhD application is the Main Round, which ends on September 1st, 2022. If you are interested in working with me, please drop me an email with your resume ASAP. Remote collaboration is also welcome!

Pinned: Highly optimized PyTorch codebases available for semantic segmentation semseg (PSPNet&PSANet).

Unified raw operator for 2D image recognition SAN and 3D point cloud recognition PointTransformerV1, V2.

Unified panoptic segmentation UPSNet (logit level), and PanopticFCN (representation level).

Unified modeling for joint 2D-3D scene recognition BPNet.

Unified tracking framework UniTrack.

Unified multi-task learning architecture MTFormer.

Publications [Google Scholar]



Professional Activities

Talks & Presentations

Honors & Awards



© Hengshuang Zhao | Last updated: 04/01/2022