Zeyu Xiao

Papers

Total Citations

H-Index

About

Zeyu Xiao is a rising researcher in multimodal perception and audio-visual understanding, with a focus on advancing semantic segmentation through innovative spatio-temporal fusion techniques. His most cited work, “ALOHA: Adapting Local Spatio-Temporal Context to Enhance the Audio-Visual Semantic Segmentation” (2025), addresses a critical challenge in pixel-level multimodal perception—moving beyond conventional global fusion modules to leverage local spatio-temporal context for more precise audio-visual integration. This contribution has direct implications for real-world systems like robotic navigation and autonomous driving, where robust scene understanding from complementary sensory inputs is essential. With 2 citations already in its early publication stage, Xiao’s work signals growing recognition of his approach to refining how machines interpret dynamic environments through sound and sight. His research bridges computer vision and audio processing, offering a pathway to more adaptive and context-aware AI. As an emerging voice in this interdisciplinary field, Xiao is poised to influence next-generation perception systems that require seamless, real-time fusion of heterogeneous data streams.