Xinxin Liang
Papers
1
Total Citations
2
H-Index
1
About
Dr. Xinxin Liang is a pioneering researcher at the intersection of cognitive manufacturing and computer vision, with a focus on enabling intelligent systems to perceive and reason about complex industrial environments. Her most notable contribution is the development of ManufVisSGG, a novel vision-language-model approach for cognitive scene graph generation in manufacturing systems. This work, published in 2024, addresses a critical gap in how machines and robots understand objects and their spatial relationships within dynamic factory settings. Unlike traditional methods that rely solely on detection or panoptic segmentation, Liang’s approach integrates language models to create richer, more interpretable scene representations. While her citation count is still growing—reflecting the recency of her work—the foundational nature of ManufVisSGG positions it as a key reference for future research in cognitive robotics and Industry 4.0. Liang’s research is particularly impactful for advancing human-robot collaboration, where machines must not only see but also comprehend context. Her work promises to transform how autonomous systems operate in unstructured manufacturing scenarios, making her a rising voice in the field of embodied AI and smart manufacturing.
Research Focus
Key Achievements
Top Papers
- 1