Sz-Rung Shiang

Papers

Total Citations

H-Index

About

Sz-Rung Shiang is a researcher working at the intersection of computer vision and natural language processing, with a primary focus on vision-language fusion for object recognition. In their most-cited work, "Vision-Language Fusion for Object Recognition" (2017, 6 citations), Shiang developed an algorithm that integrates human-generated contextual information with traditional vision algorithms to improve object recognition accuracy. This contribution addresses a key limitation in modern computer vision: while recognition rates have improved dramatically, systems still struggle with nuanced or ambiguous visual contexts. By fusing linguistic cues with visual data, Shiang’s work offers a pathway toward more robust, human-like perception in AI systems. Though early in their career, Shiang’s research demonstrates a thoughtful approach to bridging modalities, and their work has been cited in subsequent studies exploring multimodal learning. As the field increasingly turns toward embodied AI and human-in-the-loop systems, Shiang’s contributions to vision-language integration represent a foundational step in making machines better understand the world as humans describe it.