— This paper describes a speaker detection system using cross-modal association methods. Four association approaches are designed using linear and nonlinear association models. Speaker detection experiments were conducted to compare the approaches.
We propose a new approach for semantics-based image retrieval. We use color-texture classification to generate the codebook which is used to segment images into regions. The content of a region is characterized by its self-saliency and the lower-level features of the region, including color and texture. The context of regions in an image describes their… (More)
Although a variety of techniques have been developed for content-based image retrieval (CBIR), automatic image retrieval by semantics still remains a challenging problem. We propose a novel approach for semantics-based image annotation and retrieval. Our approach is based on the monotonic tree model. The branches of the monotonic tree of an image, termed as… (More)
Automatically discovering repetitive clips from large video database is a challenging problem due to the enormous computational cost involved in exploring the huge solution space. Without any <i>a priori</i> knowledge of the contents, lengths and total number of the repetitive clips, we need to discover all of them in the video database. To address the… (More)
With the increasing number of geographical image databases on the Internet, it is a very important issue to know about the most relevant image databases for given user queries, in order to achieve high efficiency in retrieving the images. To address this problem, we have developed a novel system, Webview, which intelligently ranks the distributed… (More)
State-of-art image retrieval techniques have been developed to support high-level (semantics) querying and browsing of images. For certain user queries, it is also very important to know about the information about the remote image databases on the Internet so that the queries can be guided toward the most relevant databases. In this paper, we introduce a… (More)
Over-segmentation could be relieved by adopting a divisive image segmentation model. This also requires the binary classification of whether a segmented region corresponds to a single semantic object. In this paper, we propose a model to address this classification problem, by detecting if a region contains both " background " and " foreground " regions.… (More)
1 Introduction Content-based image retrieval using low-level features such as color, texture and shape has been well studied. Various image querying systems have been built based on the low-level features for general or specific image retrieval tasks. The application of these approaches in geographic images have been explored, e.g. . However, retrieving… (More)