Special Issue on Learning from Weakly or Webly Supervised Data

Submission Deadline: Oct. 30, 2019

This special issue currently is open for paper submission and guest editor application.

Please download to know all details of the Special Issue

Special Issue Flyer (PDF)

  • Special Issue Editor
    • Yazhou Yao
      Computer Vision Research Group, Inception Institute of Artificial Intelligence, Abu Dhabi, United Arab Emirates
    Guest Editors play a significant role in a special issue. They maintain the quality of published research and enhance the special issue’s impact. If you would like to be a Guest Editor or recommend a colleague as a Guest Editor of this special issue, please Click here to fulfill the Guest Editor application.
    • Fumin Shen
      School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
    • Jian Zhang
      Global Big Data Technologies Center, University of Technology Sydney, Sydney, Australia
    • Jun Li
      Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, USA
    • Fengchao Xiong
      College of Computer Science, Zhejiang University, Hangzhou, China
    • Xiangbo Shu
      School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China
    • Jingsong Xu
      Global Big Data Technologies Center, University of Technology Sydney, Sydney, Australia
    • Fang Zhao
      Computer Vision Research Group, Inception Institute of Artificial Intelligence, Abu Dhabi, United Arab Emirates
    • Guosen Xie
      Computer Vision Research Group, Inception Institute of Artificial Intelligence, Abu Dhabi, United Arab Emirates
    • Lizhong Ding
      Computer Vision Research Group, Inception Institute of Artificial Intelligence, Abu Dhabi, United Arab Emirates
    • Tianfei Zhou
      Computer Vision Research Group, Inception Institute of Artificial Intelligence, Abu Dhabi, United Arab Emirates
  • Introduction

    In the past few years, labeled image datasets have played a critical role in high-level image understanding. For example, ImageNet has acted as one of the most important factors in the recent advance of developing and deploying visual representation learning models. However, the process of constructing ImageNet is both time-consuming and labor-intensive. To reduce the time and labor costs of manual annotation, some works also focused on weakly supervised learning. To further reduce the cost of manual annotation, learning directly from the web data has attracted more and more people's attention. Compared to manual-labeled image datasets, web images are a rich and free resource. For arbitrary categories, the potential training data can be easily obtained from the image search engines like Google or Bing. Unfortunately, due to the error index of the image search engine, the precision of returned images from an image search engine is still unsatisfactory. Original research papers are solicited in any aspect of weakly supervised or webly-supervised learning are welcome.

    Aims and Scope:

    1. Weakly supervised learning
    2. Webly supervised learning
    3. Image classification
    4. Object detection
    5. Deep convolutional neural networks
    6. Clustering based methods

  • Guidelines for Submission

    Manuscripts can be submitted until the expiry of the deadline. Submissions must be previously unpublished and may not be under consideration elsewhere.

    Papers should be formatted according to the guidelines for authors (see: http://www.eeejournal.org/submission). By submitting your manuscripts to the special issue, you are acknowledging that you accept the rules established for publication of manuscripts, including agreement to pay the Article Processing Charges for the manuscripts. Manuscripts should be submitted electronically through the online manuscript submission system at http://www.sciencepublishinggroup.com/login. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal and will be listed together on the special issue website.

  • Published Papers

    The special issue currently is open for paper submission. Potential authors are humbly requested to submit an electronic copy of their complete manuscript by clicking here.

  • Browse journals by subject