Multimedia Communications lab is engaged in research related to theories, algorithms and applications of multimedia processing and communications.

Current research activities of the lab include:

  1. Computer vision and deep learning
    • Object detection, recognition and tracking using deep learning.
    • Semantic segmentation and action recognition using deep learning.
    • Depth map estimation and processing using deep learning.
    • Multi-cue pedestrian detection and tracking.

  2. Image/video processing and communication
    • Low-complexity, error-resilient video coding.
    • Compressed video sensing.
    • Multi-view video coding, processing and transmission.

  3. Computer vision for robotics
    • Real-tome 3D reconstruction using RGB-D.
    • RGB-D simultaneous localization and mapping.
    • Large-scale 3D scene modeling.

To learn more about our research, please click here.

Graduate RA position announcement (Position available immediately):
I am seeking two PhD students (or highly qualified MS students) to work on camera-based artificial intelligence systems for autonomous cars. The project involves developing object recognition and scene understanding algorithms based on convolutional neural networks and recurrent neural networks for autonomous cars. Candidates must have a MS degree in Electrical and Computer Engineering or Computer Science. Applicants are required to have strong background in image/video processing and computer vision, good programming skills, good oral and written communication skills, and the ability to work well independently as well as in a team environment. Please send your detailed CV to Prof. Joohee Kim.