Zheheng Jiang

Papers

Total Citations

136

H-Index

About

Zheheng Jiang is a computer vision researcher whose work sits at the intersection of deep learning, underwater imaging, and object detection. His research addresses one of the more challenging frontiers in visual recognition: developing robust detection systems capable of operating in complex underwater environments, where poor visibility, image blur, and small object sizes confound conventional methods. Jiang's most recognized contribution is his development of the Invert Multi-Class Adaboost framework combined with deep learning architectures, a novel approach designed to overcome the inherent limitations of standard object detection pipelines when applied to underwater scenes. This work has accumulated over 118 citations, reflecting its significance to the marine computer vision community. Complementing this, Jiang has advanced the field by constructing dedicated benchmark datasets that jointly address underwater image enhancement and object detection, providing researchers with standardized resources to evaluate and compare methods across both tasks. His recognition that image enhancement should be tightly coupled with high-level vision tasks, rather than treated in isolation, reflects a systems-level thinking that has shaped subsequent work in aquatic robotics and marine engineering applications. Jiang's contributions offer practical value for autonomous underwater vehicles and ocean monitoring systems.