The goal of our work is object categorization in real-world scenes. That is, given a novel image we want to recognize and localize unseen-before objects based on their similarity t...
Learning the knowledge of scene structure and tracking a large number of targets are both active topics of computer vision in recent years, which plays a crucial role in surveilla...
Xuan Song, Xiaowei Shao, Huijing Zhao, Jinshi Cui,...
—We propose a Smart Trend-Traversal (STT) protocol for RFID tag arbitration, which effectively reduces the collision overhead occurred in the arbitration process. STT, a Query Tr...
We propose a technique for text document tracking over a large range of viewpoints. Since the popular SIFT or SURF descriptors typically fail on such documents, our method conside...
We propose an online anomal movement detection method using incremental unsupervised learning. As the feature for discrimination, we extract the principal component of the spatio-...