Projects
Featured Projects
NVIDIA Smooth Motion
Core contributor to NVIDIA's driver-level frame generation solution.
Deep Learning Based Video Compression
Proposed a novel CNN utilizing partition information in video encoder to enhance compressed videos (deblocking). Achieved about 10% bitrate saving on benchmark sequences. Paper accepted by ICIP 2019 (oral) and won 2nd prize in ChinaMM 2018 challenge.
Intelligent Surveillance System
Established a dataset for human fall detection. Developed a real-time deep learning based fall detection algorithm with over 80% accuracy. Won "Best Demo of the Year" award at Microsoft Research Asia Symposium in 2017.
Adaptive lossless compression of skeleton sequences
Implemented a lossless compression method for skeletons data in videos based on spatial and temporal correlation. Achieved about 84% compression ratio on test surveillance sequences. Published two papers and had one proposal accepted.