Department of Computer Science & Engineering
School of Engineering
Santa Clara University
Office: Bergin Hall 1st Floor, Santa Clara University, Santa Clara, CA 95053
Phone: +1(408) 551-3696
Email: yliu15@scu.edu; yingliuub@gmail.com.
Find me at: Google Scholar, Research Gate
The Video and Image Processing (VIP) Lab is now recruiting motivated Ph.D. students to do research in deep learning-based image and video processing. If you are interested, please send an email to Dr. Ying Liu with your CV, GRE scores, TOEFL/IELTS/Duolingo scores for international students, undergraduate and graduate transcripts, published papers if any, and potential enrollment date.
July 2025, Calvin Dong presented his paper BEV-MMC: Bird's-Eye-View-Based Multimodal Compression for Enhanced Visual Recognition at ICME 2025, Nantes, France.
June 2025, Dr. Ying Liu delivered an APSIPA Distinguished Lecturer Talk ``Conditional Information-Aware Neural Image and Video Coding". The event was hosted by the APSIPA Taiwan Chapter.
Mar. 2025, Zhongpeng's paper Blur CLIP Context Model-Based Image Coding for Machines Framework With Down and Up Sample Pairs for Multitasks is published in IEEE Access. Congratulations to Zhongpeng!
Jan. 2025, Ph.D. student Zhongpeng Zhang has passed the Oral Comprehensive Exam. Congratulations to Zhongpeng!
Jan. 2025, Dr. Ying Liu has been appointed as the 2025-26 Distinguished Lecturer of the Asia-Pacific Signal and Information Processing Association (APSIPA).
Jan. 2025, Dr. Ying Liu has been appointed as the Vice Chair of the Asia-Pacific Signal and Information Processing Association (APSIPA) US Local Chapter.
Jan. 2025, Zhongpeng's paper Side information-driven image coding for hybrid machine-human vision is published in the EURASIP Journal on Image and Video Processing. Congratulations to Zhongpeng!
Nov. 2024, Ph.D. student Tianma Shen has passed the Oral Comprehensive Exam. Congratulations to Tianma!
Oct. 2024, Dr. Ying Liu attended ICIP 2024 in Abu Dhabi, UAE and presented paper Parallel Task-Prompts ICM: A Versatile Feature Codec for Machine Vision.
Aug. 2024, Dr. Ying Liu has been appointed as the Publicity Committee Co-Chair of the IEEE Visual Signal Processing and Communications Technical Committee (IEEE VSPC TC).
Aug. 2024, Dr. Ying Liu has served as the Publication Chair of the IEEE 26th International Workshop on Multimedia Signal Processing (MMSP).
June 2024, Pengli Du has successfully passed her Ph.D. dissertation defense. She is the first Ph.D. graduate from the VIP lab. Congratulations to Dr. Du!
June 2024, Dr. Ying Liu is the recipient of the 2023-24 Researcher of the Year Award in the School of Engineering, Santa Clara University.
May 2024, Dr. Ying Liu served as the Session Chair of ``Algorithms & Hardware for Low-complexity Visual Signal Processing'' in ISCAS 2024, Singapore.
May 2024, Dr. Ying Liu has been appointed as the Publicity Committee Co-Chair of the IEEE Multimedia Systems and Applications Technical Committee (IEEE MSA TC).
Jan. 2024, Tianma's paper Learning-based conditional image compression and Zhongpeng's paper Redundancy removal module for reducing the bitrates of image coding for machines are accepted by the IEEE Int. Symp. Circuits and Systems (ISCAS), which is to be held in Singapore, May 2024. Congratulations to Tianma and Zhongpeng!
Nov. 2023, congratulations to Calvin who has passed the Ph.D. preliminary exam!
Sept. 2023, congratulations to Pengli who has passed the Ph.D. oral comprehensive exam! Another milestone towards her Ph.D. degree!
May 2023, Dr. Ying Liu served as the Session Chair of ``Learning-based Visual Signal Coding & Processing'' in ISCAS 2023, Monterey, CA.
May 2023, Ph.D. stuent Tianma Shen presented his paper ``Learned Image Compression with Transformers'' in SPIE Defense + Commercial Sensing,
Conference: Big Data V: Learning, Analytics, and Applications Orlando, FL. He has won
the Best Student Paper Award!
Mar. 2023, Dr. Ying Liu moderated an APSIPA panel discussion on Visual Coding for Machines.
Feb. 2023, one paper accepted by the International Journal of Advanced Manufacturing Technology.
Jan. 2023, Dr. Ying Liu is appointed as the Secretary/Treasurer of the Asia-Pacific Signal and Information
Processing Association (APSIPA) US Chapter.
Dec. 2022, in the 36th Picture Coding Symposium held in San Jose, CA,
Pengli presented her paper "Generative video compression with a transformer-based discriminator", and Zhongpeng presented his paper "Side information driven image coding for machines".
Pengli and Zhongpeng, well done!
Nov. 2022, in the Western Region Robotics Forum (WRRF) Conference,
the VIP team delivered a presentation
"Artificial Intelligence and Computer Vision"
to Bay Area high schoolers, older middle schoolers and their mentors.
Nov. 2022, congratulations to Tianma and Zhongpeng who have passed the Ph.D. preliminary exam!
Sept. 2022, our paper "A survey of efficient deep learning models for moving object segmentation" is accepted
by the APSIPA Transactions on Signal and Information Processing. Hard work paid off!
July 2022, Pengli's paper and Zhongpeng's paper are accepted by the 36th Picture Coding Symposium. Congratulations to Pengli and Zhongpeng!
May 2022, Dr. Ying Liu attended the IEEE International Symposium on Circuits and Systems (ISCAS) in Austin, TX.
She co-authored the paper "A lightweight model with separable CNN and LSTM for video prediction".
Apr. 2022, our project "Image Enhancement Through Transformers"
has received the 2022 Kuehler Grant from the School of
Engineering, Santa Clara University. Junior student Junhe (Timothy) Cui will be sponsored by this grant and participate in the project in Summer 2022!
Mar. 2022, the VIP team has received an NVIDIA Academic Hardware Grant. Thank Nvidia!
Dec. 2021, Dr. Liu (PI) has received an NSF award: "ERI: Generative Adversarial Networks for Video Coding,"
for the period 2/1/2022-1/31/2024 (estimated).
Dec. 2021, congratulations to Pengli that her paper "A generative adversarial network for video compression" is accepted by the SPIE Defense + Commercial Sensing Conference!
Dr. Ying Liu served as the Publicity Chair in the symposium Organizing Committee and
the Session Chair of Thursday afternoon session
"T3: Learning-Based Compression".
Video cameras are proliferating at an astonishing rate in recent years. It is predicted that the number of cameras the world will see in 2030 is approximately 13 billion. The huge amount of visual data can be leveraged in a wide range of
existing and future applications ranging from mobile video sharing, body-worn cameras, to city
surveillance and autonomous vehicles. Recent advances in deep learning have achieved great
success in computer vision tasks. The Video and Image Processing Lab currently focuses on deep learning-based image and video compression, visual coding for machines, point cloud coding, vision-language model, and generative AI. The tools we are using involve but are not limited to: convolutional neural network (CNN), generative adversarial network (GAN), recurrent neural networks (RNN), transformers, large vision models, knowledge distillation, etc.
Ying Liu (PI), "ERI: Generative Adversarial Networks for Video Coding," National Science Foundation.
Nam Ling (PI) and Ying Liu (PI), "Low Complexity and High Efficiency Image and Video
Coding with Deep Learning on Heterogeneous Platforms," Kwai, Inc.
Nam Ling (PI) and Ying Liu (Co-PI), "Low Complexity and High Efficiency Image and Video Processing with Neural Network on Heterogeneous Platforms," Kwai, Inc.
Ying Liu (PI), "Video Generation via Generative Adversarial Networks," Summer Research Stipend, Santa Clara University.
Ying Liu (PI), "Deep Learning for Video Coding," School of Engineering Research Grant, Santa Clara University.
Ying Liu (PI), "Data-Driven Distributed Video Analytics," School of Engineering Research Grant, Santa Clara University. Research Grants