Shengbo Chen

Papers

Total Citations

H-Index

About

Shengbo Chen is a researcher advancing the intersection of computer vision and natural language processing, with a primary focus on visual reasoning and question generation. His most notable contribution is the introduction of "Inferential Visual Question Generation" (2022), a novel task that moves beyond simple reverse Visual Question Answering (VQA). Instead of merely generating questions from VQA datasets, Chen’s work aims to produce questions that require deeper inferential reasoning—posing challenges that can truly test both human and robotic understanding. This approach addresses a critical gap in VQG, where conventional data-driven methods often yield trivial or repetitive queries. Although his highly cited paper has garnered 7 citations to date, its conceptual impact is significant, laying groundwork for more robust evaluation of AI systems. Chen’s research is particularly valuable for students and researchers interested in building machines that not only answer questions but also ask insightful ones, pushing the boundaries of how we assess machine intelligence in visual contexts.