Vision is a major channel of human perception. Visual media, such as images, videos and geometry, plays a crucial rule in many areas like economic, education, medicine, etc. However, the visual media often comes with huge data volume and unstructured nature, posting challenges for processing and computing it. Our team focuses on the computational method for intelligent visual media processing, which includes image/video scene understanding, content editing, saliency computation, object detection, as well as reconstruction and analysis of scene geometry. For more information about our work, please refer to the publication page.
- 3 papers accepted by AAAI 2018.
- 4 papers accepted by CVPR 2017, 1 paper accepted by ICCV 2017.
- We are looking for talented students (master and PhD) to work with us in Nankai University.