Md Sirajus Salekin

Papers

Total Citations

H-Index

About

Md Sirajus Salekin is a researcher whose work sits at the intersection of computer vision, robotics, and artificial intelligence, with a particular focus on enabling machines to understand dynamic environments. His key research area is **state recognition in cooking-related images**, a critical but underexplored problem for robotic task planning and manipulation. Salekin’s major contribution is pioneering the explicit identification of object states—such as "chopped," "boiled," or "raw"—as distinct from mere object detection. His 2018 paper, "Identifying Object States in Cooking-Related Images" (47 citations), is recognized as the first to formally introduce this problem, laying the groundwork for context-aware kitchen robots. He further advanced this with his 2019 work, "Cooking State Recognition from Images Using Inception Architecture" (22 citations), which applied deep learning to classify cooking states with improved accuracy. By shifting focus from *what* an object is to *how* it is being used or transformed, Salekin’s research provides a foundational step toward robots that can actively participate in complex, multi-step tasks like cooking. His work is essential reading for anyone interested in embodied AI, robotic manipulation, or fine-grained visual understanding.