EURASIP Journal on Image and Video Processing
Visual information learning and analytics on cross-media big data
June 1, 2019 (closed)
EURASIP Journal on Image and Video Processing welcomes submissions to the thematic series on "Visual Information Learning and Analytics on Cross-Media Big Data"
We are living in the era of data deluge. Meanwhile, the world of big data exhibits a rich and complex set of cross-media contents, such as text, image, video, audio and graphics. Thus far, great research efforts have been separately dedicated to big data processing and cross-media mining, with well theoretical underpinnings and great practical success. However, studies jointly considering cross-media big data analytics are relatively sparse. This research gap needs our more attention, since it will benefit lots of real-world applications. Despite its significance and value, it is non-trivial to analyze cross-media big data due to their heterogeneity, large-scale volume, increasing size, unstructured, correlations, and noise. Visual multimedia learning, which can be treated as the most significant breakthrough in the past 10 years, has greatly affected the methodology of computer vision and achieved terrific progress in both academy and industry. From then on, deep learning has been adopted in all kinds of computer vision applications and many breakthroughs have achieved in sub-areas, like DeepFace on LFW competition for face verification, GoogleNet for ImageNet Competition for object categorization. It can be expected that more and more computer vision applications will benefit from Visual multimedia learning.
This special issue focuses on learning methods to achieve high performance Visual Multimedia analysis and understanding under uncontrolled environments in large scale, which is also a very challenging problem. Moreover, it attracts much attention from both the academia and the industry. We hope this topic will aggregate top level works on the new advances in Visual Multimedia analysis and understanding from big surveillance data. The purpose of this SI is to provide a forum for researchers and practitioners to exchange ideas and progress in related areas.
Lead Guest Editor
- Zheng Xu, The Third Research Institute of the Ministry of Public Security & Tsinghua University, China
- Junchi Yan, IBM Research, USA
- Richard Y. D. Xu, University of Technology Sydney, Australia