The new video-coding standard MPEG-4 enables content-based functionality, as well as high coding efficiency, by taking into account shape information of moving objects. A novel alg...
Abstract— We present a novel vision-based grasp point detection algorithm that can reliably detect the corners of a piece of cloth, using only geometric cues that are robust to v...
Jeremy Maitin-Shepard, Marco Cusumano-Towner, Jinn...
—In increasingly many cases of interest in computer vision and pattern recognition, one is often confronted with the situation where data size is very large. Usually, the labels ...
The goal of image segmentation is to partition an image into regions that are internally homogeneous and heterogeneous with respect to neighbouring regions. Recently, a link shifti...
Practical supervised learning scenarios involving subjectively evaluated data have multiple evaluators, each giving their noisy version of the hidden ground truth. Majority logic ...