—This paper proposes a framework for single-image super-resolution. The underlying idea is to learn a map from input low-resolution images to target high-resolution images based ...
Tag recommendation is the task of predicting a personalized list of tags for a user given an item. This is important for many websites with tagging capabilities like last.fm or de...
Multi-instance multi-label learning (MIML) is a framework for supervised classification where the objects to be classified are bags of instances associated with multiple labels....
Previous research applying kernel methods such as support vector machines (SVMs) to hyperspectral image classification has achieved performance competitive with the best available ...
Baofeng Guo, Steve R. Gunn, Robert I. Damper, Jame...
In this paper, we propose an algorithm for sustained tracking of humans, where we combine frame-to-frame articulated motion estimation with a per-frame body detection algorithm. T...