Computer Vision Research Intern

Computer Vision Research Intern

  • Number: 1-5
  • Location: Beijing

Group Overview:

The MSRA Media Computing (MC) group focuses on key research areas related to multimedia, including computer vision, audio, media compression and AI-based RTC Optimization. This description is especially for computer vision area. The researchers in MC group mainly conduct their research in three sub-areas: scene understanding, visual recognition, and visual media manipulation. Specifically, they tackle fundamental problems and promote applications including 2D/3D scene parsing, 3D reconstruction, 2D/3D object detection, video classification, video object segmentation, multi-view correspondence learning, and video enhancement and retouching. They sustain excellence in the academic area and also contribute our advanced techniques to Microsoft products, such as video background blur/replacement and together mode for virtual group meeting in Microsoft Teams. The group members have published many papers in top-tier conferences and journals in the recent years, e.g., CVPR, SIGGRAPH, ICCV, NIPS, AAAI, TPAMI, ACMMM etc.

Job Description:

Collaborate with the researchers to conduct comprehensive computer vision research, in one of the sub-areas listed as follows:

  1. Video Representation Learning, Video Object Segmentation / Video Instance Segmentation
  2. Video based optical flow estimation / depth estimation
  3. Neural Rendering, Learning-based 3D Reconstruction

Research interns will participate in all steps of the research process, including data analysis, algorithm design, algorithm implementation, experimental study, and demonstration. Research interns will have a chance to work the researchers to develop world-class AI solutions for industries, and publish papers in top-tier conferences and journals.

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++), and one of the mainstream deep learning frameworks (e.g., Tensorflow / PyTorch).
  3. Master or Ph.D. candidates major in computer science, electronic engineering, 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 video segmentation, video representation learning, 3D reconstruction, neural rendering, generative adversarial networks, are preferred.

Required Internship Duration:

At least 6 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 MC 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.