Maryam Ziaeefard

Title: Maryam Ziaeefard: Innovator in Visual Question Answering

Introduction

Maryam Ziaeefard is a prominent inventor based in Montreal, Canada. She has made significant contributions to the field of machine learning, particularly in visual question answering systems. Her innovative approach combines knowledge graphs with machine learning to enhance the understanding of images.

Latest Patents

Maryam Ziaeefard holds a patent for a "Method of and system for explainable knowledge-based visual question answering." This patent describes a method and system for generating an augmented scene graph of an image. It involves training an explainable knowledge-based visual question answering machine learning model. The process includes obtaining a scene graph that encodes spatial and semantic features of objects and their relationships within the image. An augmented scene graph is created by embedding a knowledge graph to enhance the original scene graph. The model is trained to provide answers to questions related to the image based on this augmented scene graph.

Career Highlights

Maryam Ziaeefard is currently employed at Thales SA, where she continues to develop her innovative ideas. Her work focuses on integrating advanced machine learning techniques with practical applications in visual understanding.

Collaborations

Maryam collaborates with Freddy Lecue, who is also involved in the field of machine learning and visual question answering. Their partnership enhances the research and development efforts at Thales SA.

Conclusion

Maryam Ziaeefard is a trailblazer in the field of visual question answering, with her innovative patent showcasing her expertise and dedication to advancing technology. Her contributions are paving the way for more sophisticated machine learning applications in understanding visual data.