Existing feature extraction methods explore either global statistical or local geometric information underlying the data. In this paper, we propose a general framework to learn fea...
Shuang-Hong Yang, Hongyuan Zha, Shaohua Kevin Zhou...
We introduce the notion of co-saliency for image matching. Our matching algorithm combines the discriminative power of feature correspondences with the descriptive power of matchi...
We consider object recognition as the process of attaching meaningful labels to specific regions of an image, and propose a model that learns spatial relationships between objects....
Many vision tasks are posed as either graph partitioning (coloring) or graph matching (correspondence) problems. The former include segmentation and grouping, and the latter inclu...
Interactive programs, such as GUIs or spreadsheets, often maintain dependency information over dynamically-created networks of objects. That is, each imperative object tracks not ...
Neel R. Krishnaswami, Lars Birkedal, Jonathan Aldr...