1. Home
  2. Proceedings
  3. ICME
  4. ICME 2016
2016 IEEE International Conference on Multimedia and Expo (ICME)

Robust latent poisson deconvolution from multiple imperfect features for web topic detection

Year: 2016, Pages: 1-6

Authors

Fei Tao, School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China  
Junbiao Pang, Beijing Key Laboratory of Multimedia and Intelligent Software Technology, College of Metropolitan Transportation, Beijing University of Technology, China  
Chunjie Zhang, School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China  
Liang Li, School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China  
Li Su, School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China  
Weigang Zhang, School of Computer Science and Technology, Harbin Institute of Technology, China  
Qingming Huang, School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China  
Guiping Su, School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China

Abstract

In web topic detection, detecting “hot” topics from enormous User-Generated Content (UGC) on web data poses two main difficulties that conventional approaches can barely handle: 1) poor feature representations from noisy images and short texts; and 2) uncertain roles of modalities where visual content is either highly or weakly relevant to textual cues due to less-constrained data. In this paper, following the detection by ranking approach, we address the problem by learning a robust shared representation from multiple, noisy and complementary features, and integrating both textual and visual graphs into a k-Nearest Neighbor Similarity Graph (k-N2SG). Then Non-negative Matrix Factorization using Random walk (NMFR) is introduced to generate topic candidates. An efficient fusion of multiple graphs is then done by a Latent Poisson Deconvolution (LPD) which consists of a poisson deconvolution with sparse basis similarities for each edge. Experiments show significantly improved accuracy of the proposed approach in comparison with the state-of-the-art methods on two public data sets.

Related Articles