The Picture Coding Symposium (PCS) is an international forum devoted to advances in visual data coding. Established in 1969, it has the longest history of any conference in this area. The 36th event in the series, PCS 2022, was held from December 7-9 in San Jose, California, USA, the heart of Silicon Valley and the cultural and technological epicenter of Northern California.  The conference venue was the San Jose Hilton hotel.

MCL Director, Professor C.-C. Jay Kuo, was invited to deliver a keynote speech on green coding on Dec. 7. The abstract of his keynote was “Green Coding: Low-Complexity Learning-based Image/Video Coding.” The abstract of his talk was:

“Deep-learning-based coding (or deep coding in short) has attracted much attention in recent years due to its superior rate-distortion (RD) performance. Yet, its huge computational complexity and model sizes are of concern in practical applications.  An alternative learning-based coding, called green coding, has been intensively studied in my lab for the last two and half years. Green coding targets a model size that is significantly smaller than that of deep coding. Furthermore, it has much lower decoding complexity than today’s advanced codecs, such as HEVC and VVC. It is particularly attractive for mobile devices. Green coding uses multi-grids to capture short-, mid-, and long-range correlations in images and adopts vector quantization (VQ) to leverage correlations between images. Extensive experiments are conducted to demonstrate the high RD performance and low complexity of green image coding. Its generalization to green video coding will also be discussed.”

Besides, Professor Kuo visited San Clara University on December 6. Hosted by Professor Nam Ling, he and Professor Chia-Wen Lin of National Tsinghua University gave two lectures, which were events of the US local chapter of the Asia Pacific Signal and Information Processing Association (APSIPA).