Multimedia data is everywhere! The research in the Multimedia Computing theme aims to enable computers to ‘understand’ multimedia data in the way humans perceive the world and to ‘create’ new media data. Its outcomes are of great importance for everybody to live a happy, creative, and healthy life. Here are four key research topics of this theme. Contact A/Prof Zhiyong Wang for more information on this theme.

Multimedia Retrieval

Multimedia data has been increasingly acquired in almost every domain, ranging from our daily experiences through smart phones, lecturing videos, footage of security surveillance, music performances, and sports videos, to surgical videos and brain imaging. This has imposed great opportunities for knowledge discovery from massive multimedia data and new interactions with media such as through VR and AR. The challenging tasks towards this goal include object detection, tracking, and recognition, event detection, video summarization, multi-modal retrieval, video captioning, and affective analysis. This topic is to investigate novel techniques to advance media driven data analytics and knowledge discovery.

 Human Behaviour Analysis

People are the focus in most activities captured in multimedia data such image, video, and speech; hence investigating human motion has been driven by a wide range of applications such as visual surveillance, 3D reconstruction and animation, novel human computer interaction, sports, and medical diagnosis and treatment. This topic is to address a number of challenge issues of this area in realistic scenarios, including human tracking, motion detection, recognition, modeling, animation, and synthesis to advance human behaviour analysis.

Remote Sensing Image Analysis

Remote sensing images have played a key role in many fields such as monitoring and protecting our natural environment, precision agriculture, food safety, and smart city. Due to the limitation of the current imaging technology, advanced image analysis such as unmixing, classification, and super resolution are demanded to better utilize remote sensing image data. Meanwhile, the increasing number of massive remote sensing images demands efficient algorithms in order to support timely decision-making. This topic is to investigate effective and efficient approaches to address the emerging issues in the field of remote sensing image analysis.

Multimedia Computing for Medicine and Health

Advancements on medical imaging and pervasiveness of media capable mobile devices demand translational research of multimedia computing. For example, human activity recognition and food recognition from meal images can help individuals aware of their health status and enable healthcare providers to deliver personalized diagnosis and treatment. This topic is to investigate translational innovation from multimedia computing to medicine and health, such as personalized early diagnosis and effective treatment of chronicle, and precision medicine.