Fengjun Liu

Hunan University of Science and Technology

Papers

Total Citations

H-Index

About

Fengjun Liu is a researcher at the forefront of applying deep learning to object recognition, with a particular focus on integrating temporal and contextual information. His key research areas encompass computer vision, intelligent robotics, and autonomous driving systems. Liu’s major contribution lies in pioneering the fusion of temporal sequence data with scene prior information to enhance deep learning object recognition. His most cited work, "The Fusion of Temporal Sequence with Scene Priori Information in Deep Learning Object Recognition" (2024, 3 citations), addresses a critical gap in existing technologies—namely, the underutilization of consecutive image associations and steady scene features in applications like intelligent robots and unmanned driving. By proposing a novel framework that leverages these overlooked cues, Liu has advanced the robustness and accuracy of object recognition in dynamic environments. His work holds significant promise for improving the reliability of autonomous systems, where contextual awareness is paramount. With a growing citation impact, Fengjun Liu is establishing himself as an innovative voice in the evolution of context-aware computer vision, bridging the gap between static recognition and temporally informed perception.