• EH14 4AS

    United Kingdom

Accepting PhD Students

PhD projects

• Aesthetics and emotion processing in multimedia signals
• Efficient deep learning strategies for processing gigapixel images

Willing to speak to media

20042023

Research activity per year

If you made any changes in Pure these will be visible here soon.

Personal profile

Research interests

Spans broadly the areas of computer vision and pattern recognition with a particular interest in the following scopes:

  • Affect and emotion understanding from images and videos: Facial micro-expression analysis, image aesthetics, and emotion analysis of visual media
  • Visual surveillance tasks: Activity recognition, person/group re-identification, and long-term video analytics
  • Classical image/video processing algorithms i.e. object detection and tracking, with an emphasis on machine learning/deep learning techniques, cloud-edge computing.

Undergraduate FYP Topics 2023/24 (Major in parenthesis):

  • Curriculum learning for subjective predictive tasks on multimedia data (SDS)
  • Understanding user engagement in museum TikTok videos by analysing multimedia cues (SDS)
  • Generative style transfer for brand diffusion (CS)
  • Collaborative dashcam application for road pothole detection with federated learning (CS)

Roles & Responsibilities

Programme Director, BSc Computing Science (Malaysia campus) 

Biography

Dr. John See is an Associate Professor at School of Mathematical and Computing SciencesHeriot-Watt University (Malaysia Campus). Previously, he was a Senior Lecturer at Multimedia University, Malaysia where he was the Chair of the Centre for Visual Computing (CVC), and founded the Visual Processing (ViPr) Lab. From 2017-2019, he was also a Visiting Research Fellow at Shanghai Jiao Tong University (SJTU) as a recipient of the Belt and Road Initiative Young Scientist Fellowship. He received his Bachelor, Masters and PhD degrees from Multimedia University.

Dr. See has published more than 100 articles in reputable journals and conferences such as IEEE T-PAMI, T-AC, T-MM, T-CSVT, and top-ranked computer vision and AI conferences such as CVPR, ECCV, ICCV, ACM Multimedia, AAAI and NeurIPS. He has served as chair of several workshops, special sessions and in the technical programme committee of various international conferences. Over the span of his academic career, he has received more than MYR 2.8 million in research funding from international, national, and industrial grants as Principal Investigator (PI)/Co-PI.

He currently serves as the Associate Editor of the IEEE Transactions on Multimedia, EURASIP Journal of Image and Video ProcessingIEEE Access and Frontiers in Signal Processing (Image Processing section). He is also a Member of the Association of Computing Machinery (ACM), Senior Member of IEEE, and an Elected Member of the IEEE Multimedia Systems and Applications (MSA) Technical Committee (CAS) for Term 2020-2024 and Multimedia Signal Processing (MMSP) Technical Committee (SPS) for Term 2021-2023.

Key Research Words/Phrases

Computer Vision, Pattern Recognition, Multimedia Signal Processing, Machine Learning, Deep Learning, Affective Computing

Expertise related to UN Sustainable Development Goals

In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This person’s work contributes towards the following SDG(s):

  • SDG 3 - Good Health and Well-being
  • SDG 7 - Affordable and Clean Energy
  • SDG 9 - Industry, Innovation, and Infrastructure
  • SDG 11 - Sustainable Cities and Communities

Keywords

  • QA75 Electronic computers. Computer science
  • computer vision
  • pattern recognition
  • machine learning
  • affective computing

Fingerprint

Dive into the research topics where John See is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
  • 1 Similar Profiles

Collaborations and top research areas from the last five years

Recent external collaboration on country/territory level. Dive into details by clicking on the dots or