好色tv

报告时间：4月19日（本周五）上午9：30报告地点：9教北609报告题目：Cloud-based Image Compression报告摘要：

The cloud is characterized by a large amount of computing resources, storage, and data. Imagining a cloud that collects a huge number of images, e.g. Google street view images, when you randomly take a picture with your phone on the street, you can often find some highly correlated images in the cloud that were taken at the same location at different viewpoints and angles, focal lengths, and illuminations. If you try to share the photo with friends through the cloud, it is problematic to use conventional image coding (e.g. JPEG) that usually provides only 8:1 compression ratio. It will consume a lot of precious power and network bandwidth to transmit such a high-resolution and high-quality JPEG image. It would be more convenient to take advantage of the cloud for compression and transmission if there is a high probability of finding very similar images in the cloud. Current image coding schemes make it hard to utilize external images for compression even if highly correlated images can be found in the cloud. To solve this problem, we propose a method of cloud-based image coding that is different from cur-rent image coding even on the ground. It no longer compresses images pixel by pixel and instead tries to describe images and re-construct them from a large-scale image database via the descriptions. First, we describe an input image based on its down-sampled version and local feature descriptors. The descriptors are used to retrieve highly correlated images in the cloud and identify corresponding patches. The down-sampled image serves as a target to stitch retrieved image patches together. Second, the down-sampled image is compressed using current image coding. The feature vectors of local descriptors are predicted by the corresponding vectors extracted in the decoded down-sampled image. The predicted residual vectors are compressed by transform, quantization, and entropy coding. The experimental results show that the visual quality of reconstructed images is significantly better than that of intra-frame coding in HEVC and JPEG at thousands to one compression.报告人简介：

Xiaoyan Sun received the B.S., M.S. and Ph.D. degrees in Computer Science from Harbin Institute of Technology, Harbin, China, in 1997, 1999 and 2004, respectively. Since 2004, she has been with Microsoft Research Asia, Beijing, where she is currently a Lead Researcher with the Internet Media Group. Her research interests include video/image compression, video streaming and multimedia processing. She has authored and co-authored over 50 papers published in journals like IEEE Transaction on Image Processing, IEEE Transactions on Circuits and System for Video Technology, IEEE Transactions on Multimedia and some other International Conferences and Forums, e.g., DCC, ICIP, ICME, VCIP, and ISCAS. As a co-author, she got the best paper award in IEEE T-CSVT 2009. In addition, she has been an active contributor to ISO/MPEG and ITU-T standards. She has submitted several proposals and contributed techniques to MPEG-4 and H.264. She has over 10 U.S. patents granted or pending in video and image coding. She has been a senior member of IEEE. She serves as a reviewer for IEEE Transactions on Circuits and System for Video Technology, IEEE Transactions on Multimedia and several other International journals. She also serves as a member of the technical program committee of several conferences, e.g. ICME, ICIP, PCM, VCIP and et al.