Multimedia Signal Processing

Images, video, speech, audio, point clouds, light and sound fields… useful information is buried in these signals. We study and develop methods to efficiently sample and represent these signals, remove noise from them, compress them, and recover their missing pieces.

Selected Publications

C. Dinesh, I. V. Bajić, and G. Cheung, Adaptive nonrigid inpainting of 3D point cloud geometry, IEEE Signal Processing Letters, Jun. 2018. [ResearchGate] [code]
H. Khalilian, I. V. Bajić, and R. G. Vaughan, A simulation study of a 3D sound field reproduction system for immersive communication, IEEE/ACM Trans. Audio, Speech, and Language Processing, May. 2017. [ResearchGate] [Code]
D. Zhang and J. Liang, Graph-based Transform for 2D Piecewise Smooth Signals with Random Discontinuities, IEEE Trans. Image Processing, Apr. 2017. [IEEEXplore] []

Multimedia Communications

With the likes of Netflix, Spotify, and Skype, multimedia communications have become mainstream. But achieving dependable real-time transfer of multimedia signals is still a challenge, especially in the case of demanding immersive applications. We create techniques for error-resilient coding, power and resource management, and error control, to enable efficient and reliable multimedia communications.

Selected Publications

J. Zhang, A. Wang, J. Liang, H. Wang, S. Li, and X. Zhang, Distortion Estimation-based Adaptive Power Allocation for Hybrid Digital-Analog Video Transmission, IEEE Trans. Circuits and Systems for Video Technology, Jun. 2019. [IEEEXplore] []
G. Javadi, A. Hajshirmohammadi, and J. Liang, Power and Sub-channel Optimization of JPEG 2000 Image Transmission over OFDM-Based Cognitive Radio Networks, Signal Processing: Image Communication, Oct. 2017. [ScienceDirect] []
C. Bi and J. Liang, Joint Source-Channel Coding of JPEG 2000 Image Transmission Over Two-Way Multi-Relay Networks, IEEE Trans. Image Processing, Jul. 2017. [IEEEXplore] []

Multimedia Ergonomics

The word ergonomics probably makes you think about comfortable chairs or pillows. But physical objects are not the only things we interact with. You likely spend a good portion of each day looking at images or video, listening to music, or browsing websites. Are these digital objects comfortable? We want to understand how people interact with digital objects, especially multimedia signals, in order to facilitate better user experience and more seamless interaction with our digital environment.

Selected Publications

X. Shang, J. Liang, G. Wang, H. Zhao, C. Wu, and C. Lin, Color-Sensitivity-based Combined PSNR for Objective Video Quality Assessment, IEEE Trans. Circuits and Systems for Video Technology, May. 2019. [IEEEXplore] []
H. Hadizadeh and I. V. Bajić, Full-reference objective quality assessment of tone-mapped images, IEEE Trans. Multimedia, Feb. 2018. [ResearchGate] []
V. A. Mateescu and I. V. Bajić, Visual attention retargeting, IEEE MultiMedia, Mar. 2016. [ResearchGate] []

Deep Learning and Collaborative Intelligence

Deep Learning is revolutionizing the multimedia industry. We employ various forms of machine/deep learning to derive useful information from multimedia signals, even in their compressed form. We also study ways to deploy deep models efficiently, through collaborative intelligence.

Selected Publications

H. Choi and I. V. Bajić, Deep frame prediction for video coding, IEEE Trans. Circuits and Systems for Video Technology, Jun. 2019. [arXiv] []
M. Akbari, J. Liang, and J. Han, DSSLIC: Deep Semantic Segmentation-based Layered Image Compression, Proc. IEEE ICASSP'19, May. 2019. [arXiv] [code]
H. Choi and I. V. Bajić, Deep feature compression for collaborative object detection, Proc. IEEE ICIP'18, Oct. 2018. [ResearchGate] []