Abstract. In spite of over two decades of intense research, illumination and pose invariance remain prohibitively challenging aspects of face recognition for most practical applica...
Most recent research on querying and managing data streams has concentrated on traditional data models where the data come in the form of tuples or XML data. Complex types of strea...
A key problem for "face in the crowd" recognition from existing surveillance cameras in public spaces (such as mass transit centres) is the issue of pose mismatches betwe...
This paper addresses the face hallucination problem of converting thermal infrared face images into photo-realistic ones. It is a challenging task because the two modalities are o...
Most existing reranking approaches to image search focus solely on mining "visual" cues within the initial search results. However, the visual information cannot always ...