LV team wins the Best Student Paper Award at ACM MM 2018

LV team wins the Best Student Paper Award at ACM MM 2018

NUS Engineering PhD student Mr Jian Zhao (fifth from left), Asst Prof Jiashi Feng (sixth from left) and NUS Computing PhD student Mr Jianshu Li (fifth from right).

The Learning and Vision (LV) team from NUS Engineering clinched the Best Student Paper Award at ACM Multimedia (ACM MM) 2018 held in Seoul, Korea on 24 October 2018.  The project is a collaboration between the NUS Electrical & Computer Engineering Department’s LV group comprising Asst Prof Jiashi Feng, Assoc Prof Shuicheng Yan, Mr Jian Zhao, Mr Jianshu Li, and Mr Yu Cheng, as well as Assoc Prof Terence Sim from NUS School of Computing.

Their paper entitled “Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing” was one selected from a total of 209 papers accepted for the conference.  It is also one of four papers shortlisted for the prestigious award.  The team has developed a new method for computers to recognise and visually understand people in photos and videos. “While there has been a noticeable progress in the way computers perform perceptual tasks, computers still struggle with visually understanding humans in crowded scenes,” explained Mr Jian Zhao.

To combat this problem, the team developed a large-scale database of over 25,000 elaborately annotated images of people in groups of varying sizes, poses and interactions captured in real-life scenarios. The team also invented a new recognition model that can detect and segment body parts and fashion items in a crowd scene, while still being able to differentiate different identities of the subjects. The team believes that their new model and database will help drive further research and development into areas such e-commerce, person re-identification, image editing, autonomous driving, and virtual reality.

According to Mr Jian Zhao, the research shown that the team’s model outperforms current existing state-of-the-art solutions in their database and several other databases. In addition, their work tackles a novel situation with an original method and their dataset can contribute to further research into this topic.

ACM MM is the Association for Computing Machinery (ACM)’s annual top conference on multimedia, and is sponsored by the SIGMM special interest group on multimedia in the ACM. SIGMM specialises in the field of multimedia computing, from underlying technologies to applications, theory to practice, and servers to networks to devices.

November 9, 2018

LV team wins the Best Student Paper Award at ACM MM 2018