A number of recent systems for unsupervised featurebased learning of object models take advantage of cooccurrence: broadly, they search for clusters of discriminative features tha...
We propose measures to evaluate the performance of video object segmentation and tracking methods quantitatively without ground-truth segmentation maps. The proposed measures are ...
—We describe an approach for segmenting a moving image into regions that correspond to surfaces in the scene that are partially surrounded by the medium. It integrates both appea...
This paper proposes a new generic object recognition system based on multi-scale affineinvariant image regions. Image segments are obtained by a watershed transform of the princip...
Wei Zhang, Hongli Deng, Thomas G. Dietterich, Eric...
Video inpainting is the process of repairing missing regions (holes) in videos. Most automatic techniques are computationally intensive and unable to repair large holes. To tackle...
Sen-Ching S. Cheung, Jian Zhao, M. Vijay Venkatesh