Welcome to VENUS@ShanghaiTech!

The Visual rEasoning aNd UnderStanding (VENUS) research group at the ShanghaiTech University focuses on computational modeling of visual perception, reasoning and learning. Our main goal is to understand human visual cognition by developing inference and learning algorithms for scene understanding, and exploring its interactions with natural language processing, control/robotics and knowledge representation in general AI systems.

You may be interested in sampling the recent works, look at our research summary, publications, and so on.

  • 07/2017 Best paper award in Traffic Surveillance Workshop and Challenge@ CVPR 2017.
  • 07/2017 One paper on object segmentation accepted in ICCV 2017.
  • 04/2017 One paper on weakly supervised segmentation accepted in IJCAI 2017.