Recent years have witnessed a dramatic increase in the quantity of image data collected, due to advances in fields such as medical imaging, reconnaissance, surveillance, astronomy...
Scarcity and infeasibility of human supervision for large
scale multi-class classification problems necessitates active
learning. Unfortunately, existing active learning methods
...
Prateek Jain (University of Texas at Austin), Ashi...
Lately there exist increasing demands for online abnormality monitoring over trajectory streams, which are obtained from moving object tracking devices. This problem is challengin...
Yingyi Bu, Lei Chen 0002, Ada Wai-Chee Fu, Dawei L...
We study in this paper the problem of bridging the semantic gap between low-level image features and high-level semantic concepts, which is the key hindrance in content-based imag...
In this paper, we propose a novel transductive learning framework named manifold-ranking based image retrieval (MRBIR). Given a query image, MRBIR first makes use of a manifold ra...