Yukai Shi

Papers

Total Citations

H-Index

About

Yukai Shi is a researcher whose work lies at the intersection of computer vision and efficient deep learning, with a particular focus on lightweight object detection for intelligent robotics. His most-cited paper, "Scale-Aware Squeeze-and-Excitation for Lightweight Object Detection" (2022, 15 citations), addresses a critical challenge in deploying visual recognition systems on resource-constrained platforms. By integrating scale-aware mechanisms with squeeze-and-excitation modules, Shi's work enables high-resolution networks (HRNets) to maintain robust detection performance while dramatically reducing computational overhead. This contribution is especially valuable for real-time robotics applications, where limited hardware resources must still support accurate environmental perception. Though early in his career, Shi's research demonstrates a clear trajectory toward bridging the gap between state-of-the-art representation learning and practical deployment constraints. His work on balancing model efficiency with representational power positions him as an emerging voice in the development of deployable vision systems, offering solutions that could accelerate the adoption of intelligent perception in autonomous robots and edge devices.