One of the fundamental problems in Content-Based Image Retrieval (CBIR) has been the gap between low-level visual features and high-level semantic concepts. To narrow down this gap...
In this article, we focus on the problem of large-scale instance-level image retrieval. For efficiency reasons, it is common to represent an image by a fixed-length descriptor w...
Abstract. This paper describes a novel interaction technique to support content-based image search in large image collections. The idea is to represent each image as a vertex in a ...
In this paper, we develop a theoretical understanding of multi-sensory knowledge and user context and their interrelationships. This is used to develop a generic representation fr...
Activity recognition in video is dominated by low- and mid-level features, and while demonstrably capable, by nature, these features carry little semantic meaning. Inspired by the...