automatic Object Picture collecTion via Incremental MOdel Learning

With its explosive growth, the Internet has become a key resource for users to obtain multi-media information such as images. Unfortunately, of the hundreds and thousands of images retrieved by the internet image search softwares, only a small fraction of them would be related images. How to use object recognition approach to help this out?

Project Link: OPTIMOL



UIUC-Princeton Team in Semantic Robot Vision Challenge (AAAI 07)


Image Understanding

One of my main research interests is Image Understanding. Our dream is that: one day, computer vision techniques can help visual impaired people to 'see' the world. We are trying to use high level computer vision techniques to interpret an image in a semantic way. Hopefully, this can push us a little closer to our dream.

Total Scene Understanding


Given an image, we propose a hierarchical generative model that classifies the overall scene, recognizes and segments each object component, as well as annotates the image with a list of tags.

Full Text: PDF (CVPR09) PPT


Event Understanding

Based on the success of scene understanding and object recognition, we take a further step to interpret a static event image. Specifically, we are interested in the sports event understanding. As the first attempt, there are still some open issues. Questions and Comments are welcome.

Full Text: PDF (ICCV07)

Other Projects

Besides these, I also worked on a few small projects.

Multi-modal Message Classification Using multiple cues to understand an image.

Spam detection Applying natural language processing techniques to solve the junk email problem.