Zhaofeng Shi

University of Electronic Science and Technology of China

Papers

Total Citations

H-Index

About

Dr. Zhaofeng Shi is a rising researcher in multimodal machine perception, with a primary focus on audio-visual segmentation (AVS) and cross-modal reasoning. His most-cited work, "Cross-Modal Cognitive Consensus Guided Audio–Visual Segmentation" (2024, 4 citations), introduces a pioneering framework that aligns auditory and visual cues to precisely segment sounding objects in video frames. This contribution addresses a critical challenge in multi-modal video editing, augmented reality, and intelligent robotics, where machines must understand which object in a scene produces a given sound. By proposing a cognitive consensus mechanism, Dr. Shi’s research advances the field’s ability to fuse heterogeneous sensory data, enabling more robust and context-aware AI systems. His work has already garnered attention for its innovative approach to bridging the semantic gap between audio and visual modalities. As an early-career scholar, Dr. Shi’s contributions lay the groundwork for future breakthroughs in embodied AI and human-computer interaction, demonstrating significant potential for real-world applications in autonomous systems and immersive media.