Chen Hangong

Papers

Total Citations

H-Index

About

Chen Hangong has made significant contributions to the field of computer vision, with a primary focus on object detection and recognition in indoor environments. Their most cited work, "Indoor object recognition based on YOLOv5 with EIOU loss function" (2023), introduces a refined loss function—the Efficient Intersection over Union (EIOU)—to enhance the training efficiency and accuracy of YOLOv5 models. This innovation addresses critical challenges in large-scale object classification, such as slow convergence and suboptimal model precision, by optimizing the gradient flow during training. The paper’s 3 citations, while modest, underscore its emerging relevance in practical applications like robotics and smart home systems. Chen’s research bridges theoretical advances in loss function design with real-world deployment, offering a scalable solution for indoor scene understanding. Their work exemplifies how targeted algorithmic improvements can reduce computational costs while boosting performance, a key concern for resource-constrained environments. As an early-career researcher, Chen Hangong is establishing a reputation for pragmatic, impact-driven computer vision research, with potential for broader influence in autonomous systems and human-computer interaction.