Recent Research on Brain-Inspired Modeling and its Applications

Share

Saliency detection is an effective way to acquire potential regions of interest that may attract human eyes, its numerous applications range from object detection and recognition, image compression, video summarization, to content-based image editing and image retrieval. Towards better grouping of objects and background, a method based on Normalized graph cut (Ncut) is proposed for saliency detection. Since the Ncut partitions a graph in a normalized energy minimization fashion, resulting eigenvectors of the Ncut contain good cluster information that may group visual contents. Motivated by this, the proposed method directly induces saliency maps via eigenvectors of the Ncut, contributing to accurate saliency estimation of visual clusters.

Given a few labelled samples, semi-supervised learning generally performs much better than supervised learning, semi-supervised learning algorithms are more robust to noise. Label Prediction via Deformed Graph Laplacian for Semi-supervised Learning is presented. A novel curriculum learning approach, dubbed multi-modal curriculum learning, to optimize the quality of semi-supervised image classification is proposed.



  Date and Time

  Location

  Contact

  Registration


  • Simon Fraser University
  • 8888 University Drive
  • Burnaby, British Columbia
  • Canada V5A 1S6
  • Building: Applied Sciences Building
  • Room Number: ASB 10940 (SFU's Big Data Visualization Lab)
  • Click here for Map

Staticmap?size=250x200&sensor=false&zoom=14&markers=49.2780937%2c 122
  • Ljiljana Trajkovic
    Professor
    School of Engineering Science
    Simon Fraser University
    8888 University Drive
    Burnaby, B.C. V5A 1S6
    Canada

    Tel.: (778) 782-3998 (office)
    FAX: (778) 782-4951
    E-mail: ljilja@cs.sfu.ca
    WWW: http://www.ensc.sfu.ca/~ljilja

  • Registration closed


  Speakers

Jie Yang

Jie Yang of Shanghai Jiaotong University

Topic:

Recent Research on Brain-Inspired Modeling and its Applications

Saliency detection is an effective way to acquire potential regions of interest that may attract human eyes, its numerous applications range from object detection and recognition, image compression, video summarization, to content-based image editing and image retrieval. Towards better grouping of objects and background, a method based on Normalized graph cut (Ncut) is proposed for saliency detection. Since the Ncut partitions a graph in a normalized energy minimization fashion, resulting eigenvectors of the Ncut contain good cluster information that may group visual contents. Motivated by this, the proposed method directly induces saliency maps via eigenvectors of the Ncut, contributing to accurate saliency estimation of visual clusters.

Given a few labelled samples, semi-supervised learning generally performs much better than supervised learning, semi-supervised learning algorithms are more robust to noise. Label Prediction via Deformed Graph Laplacian for Semi-supervised Learning is presented. A novel curriculum learning approach, dubbed multi-modal curriculum learning, to optimize the quality of semi-supervised image classification is proposed.

Biography:

Jie Yang received a bachelor's degree in Automatic Control in Shanghai Jiao Tong University, where a master's degree in Pattern Recognition & Intelligent System was achieved three years later. In 1994, he received Ph.D. at Department of Computer Science, University of Hamburg, Germany. Now he is the Professor and Director of Institute of Image Processing and Pattern recognition in Shanghai Jiao Tong University. He is the principal investigator of more than 30 national and ministry scientific research projects in image processing, pattern recognition, data mining, and artificial intelligence, including two national 973 research plan projects, three national 863 research plan projects, four National Nature Foundation projects, six international cooperative projects with France, Sweden, Korea, Japan, New Zealand. He has published five books£¬more than five hundreds of articles in national or international academic journals and conferences. Up to now, he has supervised 5 postdoctoral, 36 doctors and 66 masters, awarded six research achievement prizes from ministry of Education, China and Shanghai municipality. Two Ph.D. dissertation he supervised was evaluated as "National Best Ph.D. Dissertation" in 2009 and in 2017. Two Ph.D. dissertations he supervised were evaluated as "Shanghai Best Ph.D. Dissertation" in 2009 and 2010. He has owned 32 patents.

Email:

Address:School of Electronics and Information, Shanghai Jiaotong University, Shanghai, China, 200240