报告题目: Multiple Feature Hashing for Real-time Large Scale

报告人: Dr. Yang Yi
时间:  12月8日下午2点到3点半
地点： 信息楼四楼学术报告厅

Abstract:
     Near-duplicate Video Retrieval Near-duplicate video retrieval (NDVR) has recently attracted lots of research attention due to the exponential growth of online videos. It helps in many areas, such as copyright protection, video tagging, online video usage monitoring, etc. Most of existing approaches use only a single feature to represent a video for NDVR. However, a single feature is often insuf?cient to characterize the video content. Besides, while the accuracy is the main concern in previous literatures, the scalability of NDVR algorithms for large scale video datasets has been rarely addressed. In this paper, we present a novel approach - Multiple Feature Hashing (MFH) to tackle both the accuracy and the scalability issues of NDVR. MFH preserves the local structure information of each individual feature and also globally consider the local structures for all the features to learn a group of hash functions which map the video keyframes into the Hamming space and generate a series of binary codes to represent the video dataset. We evaluate our approach on a public video dataset and a large scale video dataset consisting of 132,647videos, which was collected from YouTube by ourselves. The experiment results show that the proposed method outperforms the state-of-the-art techniques in both accuracy and ef?ciency.

Bio:
    Yi Yang received his Ph.D degree from Zhejiang University, in Computer Science in 2010.  He worked for the University of Queensland as a postdoctoral research fellow from September 2010 to May 2011. In May 2011, he joined the School of Computer Science at Carnegie Mellon University, as a postroctoral research fellow. His research interests include machine learning and its applications to multimedia content analysis and computer vision, e.g. multimedia indexing and retrieval, image annotation, video semantics understanding, etc.