Close

We use cookies to improve your experience of our website. Privacy Policy

Skip to main content

Institute of Applied Data Science

Search
Menu

News

Sean Gong ranked inside Top 20 Computer Scientists in UK

10 June 2020

Sean Gong, Professor of Visual Computation
Sean Gong, Professor of Visual Computation
We are delighted to report that Professor Sean Gong has been ranked 19th for Computer Science in the UK by 'Guide 2 Research' in their Leading Computer Scientist List. This ranking lists all leading computer scientists affiliated with the United Kingdom and includes other eminent computer scientists from the Alan Turing Institute and its partner universities.

Our congratulations to Sean!

How Sean's field in computer vision will help Amazon customers shop online
Yanbei Chen, final-year PhD Student, and Shaogang Gong, Professor of Visual Computation, have been working in collaboration with Amazon. Their work on computer vision has been featured in this week's Amazon Science Blog. They address the challenges of using text to refine an image that matches a product query, with a neural network that’s trained on triples of inputs: a source image, a textual revision, and a target image that matches the revision.

Recent work with Amazon - Visiolinguistic product discovery
Using text to refine an image that matches a product query poses three main challenges. The first is finding a way to fuse textual descriptions and image features into a single representation. The second is performing that fusion at different levels of resolution: the customer should be able to say something as abstract as “Something more formal” or as precise as “change the neck style”. And the third is training the network to preserve some image features while following customers' instructions to change others.

Yanbei Chen was an intern at Amazon when the work was done; Chen’s advisor, Sean Gong; and Loris Bazzani, a senior computer vision scientist at Amazon, address these challenges with a neural network that’s trained on triples of inputs: a source image, a textual revision, and a target image that matches the revision. More here: https://www.amazon.science/blog/how-computer-vision-will-hel...
Link: http://www.guide2research.com/scientists/UK