Welcome to Hui Wu's website

Research Scientist, IBM Research AI

Welcome to Hui Wu's website

Profile Photo

About Hui Wu

I am a computer vision researcher at IBM Research AI, working with Dr. Rogerio Feris at the computer vision and multimedia department. I enjoy learning and developing machine learning and computer vision algorithms for real-world applications. Beyond my work on computer vision, I like thinking about the types of intelligent tools we can build to augment human capability and creativity.

Prior to joining IBM, I received my PhD in Computer Science from UNC Charlotte. There I worked with my thesis advisor Dr. Richard Souvenir (2011-2015) on applying manifold learning based machine learning techniques to computer vision problems, with a focus on echocardiogram video analysis.

Contact me: wuhu AT us.ibm.com


Selected Projects

Dialog-based Interactive Image Retrieval

Xiaoxiao Guo*, Hui Wu*, Yu Cheng, Steve Rennie, Gerald Tesauro and Rogerio Feris (* equal contribution)
Dialog-based Interactive Image Retrieval
NeurIPS 2018 [PDF] [CODE] [DEMO] [Project Page]


We proposed a novel type of dialog agent for the task of interactive image retrieval. Recently, there has been a rapid rise of research interest in visually grounded conversational agents, driven by the progress of deep learning techniques for both image and natural language understanding. A few interesting application scenarios have been explored by recent work, such as collaborative drawing, visual dialog and object guessing game. In this work, we tested the value of visually grounded dialog agents in a practical and yet challenging context. Specicially, we proposed a novel framework of image retrieval system which learns to seek natural and expressive dialog feedbacks from the user and iteratively refine the retrieval result.

Pooling with Stochastic Spatial Sampling

Zhai, Shuangfei, Hui Wu, Abhishek Kumar, Yu Cheng, Yongxi Lu, Zhongfei Zhang, and Rogerio Feris
S3pool - Pooling with stochastic spatial sampling
CVPR 2017 [PDF] [CODE] [Project Page]

Semantic-aware Food Visual Recognition

Hui Wu, Michele Merler, Rosario Uceda-Sosa and John R. Smith
Learning to make better mistakes - Semantics-aware visual food recognition
ACM Multimedia, 2016 [PDF] [Watson API] [Project Page]

The growing popularity of fitness applications and people’s need for easy logging of calorie consumption on mobile devices has made accurate food visual recognition increasingly desireable. In this project, we proposed a visual food recognition framework that integrates the semantic relationships among fine-grained food classes.