Multimodal Image and Video Manipulation Research Intern


Multimodal Image and Video Manipulation Research Intern

  • Number: 2-3
  • Location: Beijing

Group Overview:

Multimedia Search and Mining (MSM) group focuses on a wide variety of multimedia-related research and projects, e.g., understanding, analysis, search, data mining, and applications. We are working on research problems in image understanding, video analytics, large scale visual (image and video) synthesis and manipulation, 3D reconstruction, and so on. We have published many high-performing publications on ACM Multimedia, CVPR, ICCV, and NeurIPS, including the Best paper award in ACM TOMM 2017, and in ACM Multimedia 2018, etc.

Job Description:

With the emerging of pre-training models, creating or editing an image or video by cross-modal inputs (e.g. styleClip) has been a new trend. We want to hire candidate who can collaborate with the researchers in MSRA MSM to conduct comprehensive research in areas related to multimodal content creation. Co-author with the researchers in MSRA MSM to publish papers in top-tier conferences and journals, and build working demos in real scenarios.

Required Qualifications:

The candidate should have the following basic skills:

  1. Strong motivation to conduct state-of-the-art research work and publish paper in top-tier conferences and journals.
  2. Strong implementation skills in at least one of the mainstream programing languages, e.g., Python, C, Java.
  3. Master or Ph.D. candidates major in computer science, statistics, or related areas with good English reading/speaking/listening/writing skills.
  4. Candidates who have published papers in top-tier conferences or journals are preferred. Candidates who have research experiences in GAN, image and video synthesis, and pre-training models are preferred.

Required Internship Duration:

At least 3 months.

Application Process

Qualified applicants are required to fill out the application form and send it with their CVs/resumes in English (if applicable, in Chinese as well) in PDF/Word/Txt/Html format to:, and note that you are applying for  an internship position in MSRA Multimedia Search and Mining Research Group. Download the Application Form here:

To learn more about Stars of Tomorrow Internship Program, please contact We are happy to answer any question you may have.