Qi Dong

Title: Qi Dong - Innovator in Text-Based Image Search Technology

Introduction

Qi Dong is a prominent inventor based in London, GB. He has made significant contributions to the field of machine learning, particularly in the area of image search technology. His innovative approach combines text attributes with visual data to enhance search capabilities.

Latest Patents

Qi Dong holds a patent for a method and system for building a machine learning model that finds visual targets from text queries. The patent, titled "Text based image search," outlines a comprehensive method that includes receiving a set of training data with text attribute labeled images. Each image in this dataset has multiple text attribute labels. The process involves generating a visual feature vector space by grouping images with similar attribute labels and mapping these attributes onto a first vector space. The fusion of these vector spaces results in a third vector space, from which a similarity matching model is generated. This innovative approach significantly improves the accuracy and efficiency of image searches based on textual input.

Career Highlights

Qi Dong is currently employed at Veritone, Inc., where he continues to develop cutting-edge technologies in artificial intelligence and machine learning. His work at Veritone has positioned him as a key player in the advancement of intelligent search solutions.

Collaborations

Qi Dong collaborates with notable colleagues such as Shaogang Gong and Xiatian Zhu, who contribute to the innovative projects at Veritone, Inc. Their combined expertise fosters a dynamic environment for technological advancement.

Conclusion

In summary, Qi Dong is an influential inventor whose work in text-based image search technology is paving the way for more efficient machine learning applications. His contributions are shaping the future of how we interact with visual data through text queries.