What We Do

The Rapid-Rich Object Search (ROSE) Lab is a joint collaboration between Nanyang Technological University, Singapore, and Peking University, China. Its vision is to create the largest collection of structured domain object database in Asia, and to develop rapid and rich object mobile search.

Research Focus

As mobile devices such as smartphones and tablets proliferate, internet search is more frequently performed on these devices. The search giant Google generated around $1 billion from mobile search in 2010, and its mobile segment is as valuable as its desktop search division. However, current mobile search is mainly based on text, with limited capability in describing real-world objects. In many sit​uations, a picture taken with a mobile device is simply more descriptive. We believe mobile object search will be the trend in the coming years and create huge economic value and opportunities. Our object search services will be built on a media cloud platform for scalability and robustness.

 

Object Recognition & Retrieval

To enable rapid and rich mobile object search with constrained network and computational resources, compact and innovative feature coding, scalable indexing and visual search algorithms are necessary.

Deep Learning & Video Analytics

This area of research focuses on the use of traditional as well as machine learning (in particular, deep learning) approaches for video analytics.

Multimedia Forensics Biometrics

This area of research focuses on biometrics for image and video forensics application. Topics include biometrics & soft biometrics, face spoofing & liveness detection, and reflection removal.

Datasets

While some parts of our database is confidential, we do have the following datasets that are available for download upon request.

What We Develop

ROSE Lab team wins 1st Place in IEEE SPS 5-Minute Video Clip Contest on “Fight the Pandemic”

ROSE Lab Team wins 2nd Runner-up in NUS-MIT Healthcare AI Datathon 2020

You may also be interested in