Pictures Are Not Taken in a Vacuum
Jiebo Luo, Matthew R. Boutell, Christopher M. Brown · 2006
onsiderable research has been devoted to the problem of multimedia indexing and retrieval in the past decade. However, limited by the state of the art in image understanding, the majority of the existing con-tent-based image retrieval (CBIR) systems have taken a relatively low-level approach and fallen short of higher-level interpretation and knowledge. Recent research has begun to focus on bridging the semantic and conceptual gap that exists between man and computer by integrating knowledge-based techniques, human perception, scene content understanding, psychology, and linguistics. In this article, we provide an overview of exploiting context for semantic scene content understanding. Context is critical in humans ’ recognition process, where the human visual system makes extensive use of the envi-ronment to facilitate object detection (e.g., where are the pedestrians? should we look around sidewalks?) [1]. Likewise, it can be used to improve the performance of automated systems for semantic indexing and retrieval of mul-timedia data. In this article, we intend to present a unique perspective on systematically exploiting a broad array of