2010 Poster Sessions : Building and Using a Semantivisual Image Hierarchy

Student Name : Jia Li
Advisor : Fei-Fei Li
Research Areas: Artificial Intelligence
A semantically meaningful image hierarchy can ease the human effort in organizing thousands and millions of pictures (e.g., personal albums), and help to improve performance of end tasks such as image annotation and classification. Previous work has focused on using either lowlevel image features or textual tags to build image hierarchies, resulting in limited success in their general usage.
In this paper, we propose a method to automatically discover the “semantivisual” image hierarchy by incorporating both image and tag information. This hierarchy encodes a general-to-specific image relationship. We pay particular attention to quantifying the effectiveness of the learned hierarchy, as well as comparing our method with others in the end-task applications. Our experiments show that humans find our semantivisual image hierarchy more effective than those solely based on texts or low-level visual features. And using the constructed image hierarchy as a knowledge ontology, our algorithm can perform challenging image classification and annotation tasks more accurately.

I got my Bachelor degree in Automation from University of Sci&Tech of China in 2003. I am now a PhD student in the Computer Science Department at Stanford University. My thesis advisor is Professor Fei-Fei Li. Before I moved to Stanford, I worked with Professor Fei-Fei Li at University of Illinois for 2 years and Princeton University for 1 year. My research interests are in Computer Vision and Machine Learning.