We study the task of object part extraction and labeling, which seeks to understand objects beyond simply identifiying their bounding boxes. We start from bottom-up segmentation of...
In scanning photographs, receipts or other small objects users will often scan many at a time. It would be convenient to automatically detect that the scanned image consists of ma...
Real world images are complex objects, difficult to describe but at the same time possessing a high degree of redundancy. A very recent study [1] on the statistical properties of n...
Image segmentation and its performance evaluation are very difficult but important problems in computer vision. A major challenge in segmentation evaluation comes from the fundame...
Here, we present a constrained object recognition task that has been robustly solved largely with simple machine learning methods, using a small corpus of about 100 images taken u...