Visual Information Processing and Learning
Visual Information Processing and Learning


News / Events

The Lip-reading Technology is Shown on CCTV's A.I. Mission

Date of publication:2018-10-24      Number of clicks: 32

Invited by the CCTV's A.I. Mission, a famous scientific TV program, the lip-reading technology developed by the Institute of Computing Technology, is shown on the show, and acquires the title of pioneer of service. This program will be shown in 20:00, October 20, 2018. CCTV's A.I. Mission is jointly sponsored by CCTV and the Chinese Academy of Sciences, jointly produced by CCTV Comprehensive Channel, Bureau of Science Communication of the Chinese Academy of Sciences and Beijing Changjiang Culture Co., and Ltd. SF Motors is the exclusive title sponsor of this program.

    Lip-reading is one difficult topic in the computer vision domain, getting more and more attention these years. The VIPL research group started this topic in 2017. Now, an accurate and robust lip-reading system has been developed successfully, and shown in the famous forum VALSE 2018, IEEE FG 2019 and so on.

    In the deep learning era, the development and research about lip-reading could benefit much from large-scale lip-reading datasets. Therefore, the group has collected and released a large-scale Mandarin word-level lip-reading dataset, LRW-1000. This dataset is available for all research institutes, for only research use. More details about this dataset can be found athttp://vipl.ict.ac.cn/en/view_database.php?id=13.

       After the TV show, the lip-reading system has been concerned and received very good responses from various social circles, which gives the team great encouragement and confidence to perform the research about lip-reading in a much better, more thorough and much deeper way!




Visual Information Processing and Learning
  • Address :No.6 Kexueyuan South Road
  • Zhongguancun,Haidian District
  • Beijing,China
  • Postcode :100190
  • Tel : (8610)62600514
  • Email:yi.cheng@vipl.ict.ac.cn
  • Valse

  • Big Lecture of DL

Copyright @ Visual Information Processing and Learning 京ICP备05002829号 京公网安备1101080060