Project - From Appearance to Context Based Recognition
This work was done in collaboration with Larry Zitnick at Microsoft Research (Redmond)
Traditionally, object recognition is performed based solely on the appearance of the object. However, relevant information also exists in the scene surrounding the object.
Our human studies indicate that contextual information is necessary for accurate recognition in low resolution images. However, the same is not the case for high resolution images. The scenario with impoverished appearance information provides an appropriate venue for studying the role of context in recognition. In this paper, we explore the role of context for dense scene labeling in small images.
Given a segmentation of an image, our algorithm assigns each segment to an object category based on the segment’s appearance and contextual information. We explicitly model context between object categories through the use of relative location and relative scale, in addition to co-occurrence. We perform recognition tests on low and high resolution images, which vary significantly in the amount of appearance information present, using just the object appearance information, the combination of appearance and context, as well as just context without object appearance information (blind recognition).
We also perform these tests in human studies and analyze our findings to reveal interesting patterns.
With the use of our context model, our algorithm achieves state-of-the-art performance on MSRC and Corel datasets.
Further details can be found in our CVPR 2008 paper.
This video briefly describes the motivation behind this work, our contributions and the set-up for our human studies.
Any suggestions or comments are welcome. Please send them to Devi Parikh