Mr. Zushuang Liang, Harbin Institute of Technology, China
Mr. Zushuang Liang is a graduate student at the Harbin Institute of Technology, specializing in Computer Vision with a focus on Salient Object Detection and Graph Neural Networks (GNNs). His innovative research, including the development of a multi-scale graph attention network for video detection, holds promising applications in areas such as autonomous driving and surveillance. Additionally, Mr. Liang explores interdisciplinary work by integrating machine learning with music technology through piano polyphonic transcription, showcasing his versatility and contribution to both fields.
Professional Profile:
Suitability for the Best Researcher Award:
Mr. Liang’s work is not only technically innovative but also highly impactful. His contributions to video salient object detection with applications that extend to fields like autonomous driving, surveillance, and multimedia retrieval make him a deserving candidate for the Best Researcher Award. His interdisciplinary approach, combining machine learning with music technology, further distinguishes him as a forward-thinking researcher.
Educational Background:
He earned his Bachelor’s Degree from the Harbin Institute of Technology and is currently pursuing a Master’s degree at the same institution, within the School of Electronics and Information Engineering.
Area of Specialization:
Mr. Zushuang Liang specializes in Computer Vision with a focus on Salient Object Detection and Graph Neural Networks (GNNs). His work revolves around enhancing video detection accuracy by applying innovative techniques in multi-scale graph attention networks.
Research & Contributions:
His pioneering research includes developing the multi-scale graph attention network for video salient object detection, with potential applications in autonomous driving and surveillance. Additionally, he bridges disciplines by working on piano polyphonic transcription, integrating machine learning with music technology.
Publication Top Notes:
Title: DAFE-MSGAT: Dual-Attention Feature Extraction and Multi-Scale Graph Attention Network for Polyphonic Piano Transcription