Siliang Tang

Zhejiang University of Science and Technology, Zhejiang University

Papers

Total Citations

129

H-Index

About

Siliang Tang is a researcher whose work spans computer vision, ubiquitous computing, and human-robot interaction. His most impactful contribution is in infrared image super-resolution, where he developed cascaded deep networks with multiple receptive fields—a pioneering approach that achieved 103 citations for significantly enhancing low-resolution infrared imagery for critical applications like night vision and surveillance. Tang also made early contributions to ubiquitous computing with his context quality model (2007), which addressed the often-overlooked influence of external factors on Quality of Context (QoC), laying groundwork for context-aware systems. More recently, he has advanced affective computing through his work on temporal emotion localization in videos, introducing a dilated context integrated network with cross-modal consensus that enables robots to pinpoint emotional moments in video streams—a key step toward more natural human-robot interaction. With a research portfolio that bridges foundational context modeling and cutting-edge deep learning for visual and emotional understanding, Tang demonstrates a sustained commitment to making intelligent systems more perceptive and responsive to their environments.