The Multimedia Visual Processing Lab (MVP Lab) was founded by Dr. Nam Ling and is dedicated to the research of image and video coding (compression and decompression) and processing with visual processing and deep learning methods.
Besides Dr. Ling, the lab team currently consists of 8 Ph.D. students, 3 M.S. and Undergrad students, and 4 faculty collaborators. The team meets every Thursday at 12:30 p.m. to present and discuss research. MVP lab is equipped with fast multi-core workstations and GPUs, as well as different software. We collaborate with 5 universities and 1 company.
- Deep learning approaches to video coding.
- Video and image coding for machines.
- Deep learned GAN and transformer for image compression.
- Deep CNN for moving object detection.
- Deep learning for video compressive sensing.
- Sparse coding for screen content video.
Dr. Ling's Advice to Students
- Two mottos I often remind my students:
- “Work smarter, not harder!”
- “Performance is measured by results”
- My three C’s for a successful career: Our University has the three C’s (competence, conscience, and compassion) in the vision statement; I often challenge my students with my three C’s for a successful career:
- Competence (the need to have a strong set of knowledge and skills)
- Communication (the need to communicate and present yourself well)
- Connection (the need to know the right people, be connected)
- Albert Einstein’s “Three Rules of Work:
- Out of clutter find simplicity
- From discord find harmony
- In the middle of difficulty lies opportunity”
Room 311, 455 El Camino Real, Santa Clara, California, U.S.A