Dr. Ling and his lab team
Dr. Ling and his lab team
Dr. Ling - Lab team celebrating his birthday
Dr. Ling - moderating an APSIPA Panel
Dr. Ling - 56 countries and 25 top attractions visited
Dr. Ling - touching wild lions in Zimbabwe
Dr. Ling - parasailing in Thailand
Dr. Ling - snorkeling in Maldives
Dr. Ling - floating on the Dead Sea, Jordan
Dr. Ling - driving a rover in Gansu, China
Dr. Ling - tasting nice food in Yilan, Taiwan
Dr. Ling - at Red Square, Moscow, Russia
Dr. Ling - climbing at Chichen Itza, Mexico
Dr. Ling - at Machu Picchu, Peru
Dr. Ling - at Taj Mahal, Agra, India
previous arrowprevious arrow
next arrownext arrow

Introduction to Professor Nam Ling and His Lab at Santa Clara University

  1. Could you briefly introduce yourself (and your University/Lab)?

I am currently the Wilmot J. Nicholson Family Chair Professor (endowed chair) at Santa Clara University (SCU) and the Chair of its Department of Computer Science & Engineering (2010 – present). I served as the Associate Dean for SCU School of Engineering (2002 – 2010). I am/was also the Chair/Distinguished and Guest Professor at six universities internationally. I am an IEEE Fellow due to my contributions to video coding algorithms and architectures. I am also an IET Fellow. I was named IEEE Distinguished Lecturer twice and was also an APSIPA Distinguished Lecturer. I have more than 230 publications, seven adopted standards contributions, more than 20 US/PCT patents, four best paper awards, and six awards from SCU. I served as Keynote Speaker for 11 international conferences, General Chair/Co‑Chair for 11 international conferences, and Technical Program Co‑Chair for seven conferences. I chaired two IEEE technical committees, and have served as Guest Editor/Associate Editor for more than five journals. I delivered more than 120 invited colloquia in 10 countries. More details can be found on my professional website. My hobby is traveling and tasting good food from different countries. So far I have made close to 300 trips, visited 56 different countries, in six continents. I have also published a travel book and am finishing another one.

My research lab, the MVP Lab (Multimedia Visual Processing Lab) is dedicated to the research on image and video coding and processing, current projects involve using deep learning approaches in image/video coding, video compressive sensing, and object detection. The lab team consists of eight PhD students, one Engineer’s degree student, three MS and undergrad students, and four faculty collaborators. We also collaborate with other universities worldwide. The lab is equipped with high-performance multi-core workstations and GPUs, as well as different software. More details can be found on my lab website.

My university, Santa Clara University, is a Jesuit University in the heart of Silicon Valley. Established in 1851, it is the oldest university in California. Currently it is ranked #53 among National Universities and #25 in Best Undergraduate Teaching, according to the 2021 U.S. News & World Report ranking.

  1. What have been your most significant research contributions up to now?

Our most significant research contributions have been in the area of video coding. Three areas with the most significant contributions are: (a) Our frame-layer video rate control and Lagrange multiplier/quantizer adjustment schemes have been cited by many papers and used in the industry. (b) Our fast motion estimation scheme, named Simplified and Unified Multi-Hexagon Search (SUMH), has been adopted by H.264/AVC international standard into the JM software, as one of the four fast motion estimation choices. (c) Our work on depth intra coding for 3D video has made quite an impact with five contributions adopted (two as normative) by the 3D-HEVC standard and into the HTM software.

  1. What problems in your research field deserve more attention (or what problems will you like to solve) in the next few years, and why?

Most of our current and near-future research projects focus on using deep-learning approaches in image and video coding and processing as well as in certain computer vision problems such as moving object detection. We investigate the potential of deep models to achieve superior bit-rate saving and visual quality improvement compared with traditional methods, while achieving low complexity and latency in short video services. We leverage tools such as convolutional neural networks (CNNs), generative adversarial networks (GANs), transformers, and reinforcement learning. The key problem we try to solve is how to achieve low computational complexity for fast encoding/decoding/processing and power saving, while improving coding efficiency.

  1. What advice would you like to give to the young generation of researchers/engineers?

“Work smarter, not harder!” and “Performance is measured by results” are the two mottos I often remind my students. Our University has the three C’s (competence, conscience, and compassion) in its vision statement; I often challenge my students and the younger generation 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), and connection (the need to know the right people, be connected). For young researchers, I also share with them Albert Einstein’s “Three Rules of Work: (1) Out of clutter find simplicity. (2) From discord find harmony. (3) In the middle of difficulty lies opportunity.”