Qingbo Wu

University of Electronic Science and Technology of China

Papers

Total Citations

H-Index

About

Qingbo Wu is a leading researcher in multimodal perception and computer vision, with a focus on audio-visual segmentation (AVS)—a task that extracts sounding objects from video frames to enable applications like multi-modal video editing, augmented reality, and intelligent robotics. His pioneering work, "Cross-Modal Cognitive Consensus Guided Audio–Visual Segmentation" (2024), introduces a novel framework that leverages cognitive consensus between audio and visual modalities to achieve precise pixel-wise segmentation, addressing a critical gap in cross-modal understanding. With over 4 citations in its first year, this paper has quickly become a foundational reference in the field. Wu’s contributions extend to advancing how machines integrate auditory and visual cues, pushing the boundaries of human-like perception in AI systems. His research is widely recognized for its impact on intelligent robot systems and augmented reality, where accurate audio-visual alignment is essential. Through his innovative approaches, Wu continues to shape the future of multimodal learning, inspiring new directions in interactive AI and scene understanding.