IEEE SPS NSW Webinar Series 2026–27: Inaugural Keynote Talk
Join the IEEE New South Wales Signal Processing Society Chapter for an online seminar by Professor Manoranjan Paul from Charles Sturt University.
Date: Wednesday, 28 October 2026
Time: 5:30–6:30 pm AEDT (Sydney time)
Venue: Online via Zoom:
LINK: https://cqu.zoom.us/j/85106607089?pwd=mUcbbLO9bawrKvdNsMnaG1ainQEzwO.1
Speaker Profile: Professor Manoranjan Paul
Professor Manoranjan Paul is a Professor of Computer Science at Charles Sturt University, Director of its Computer Vision Lab, and Head of the Machine Vision and Digital Health Research Group. An award-winning researcher, he received the ACS ICT Researcher of the Year and Golden Disruptor awards in 2017. He has published around 200 peer-reviewed publications, supervised 16 PhD completions, and secured $3.6 million in competitive external research funding. He serves as an Associate Editor for leading IEEE and EURASIP journals and is a Senior Member of IEEE and ACS.
Title: AI That Thinks Differently: Seeing, Understanding, and Trusting Visual Data in the Age of Foundation Models
Visual data now underpins healthcare, agriculture, autonomous systems and everyday communication, yet it remains costly to store and transmit, difficult to interpret at a fine-grained level, and increasingly easy to fake. This talk presents our group's research on AI that thinks differently about how machines perceive, represent and reason over visual content. Drawing on years of work in digital health, environmental sensing and intelligent systems, I show that domain knowledge, structure-aware design and careful handling of noisy, real-world data are what turn accurate models into reliable, deployable ones. Building on this foundation, I present our recent efforts along four connected themes: efficient representation, where a "compress once, adapt many" paradigm allows a single compact encoding of video and 3D data to serve many downstream machine vision tasks; fine-grained understanding, where vision-language models are guided to link visual parts with semantic descriptions, even with few examples; spatio-temporal reasoning, where compact, task-aware video representations support efficient question answering; and authenticity, where structural cues are used to expose the subtle traces left by generative models in fake images. Together, these themes outline a path toward visual AI that is efficient, discriminative and trustworthy. I conclude with open challenges and opportunities for collaboration, including unified multimodal pipelines and emerging computing paradigms for imaging.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
Loading virtual attendance info...
- Contact Event Host
-
For enquiries, contact Dr Anwaar Ulhaq at a.anwaarulhaq@cqu.edu.au.
- Starts 01 October 2026 02:00 PM UTC
- Ends 27 October 2026 01:00 PM UTC
- No Admission Charge
Speakers
Professor Manoranjan Paul
Title: AI That Thinks Differently: Seeing, Understanding, and Trusting Visual Data in the Age of Foundation Models
Visual data now underpins healthcare, agriculture, autonomous systems and everyday communication, yet it remains costly to store and transmit, difficult to interpret at a fine-grained level, and increasingly easy to fake. This talk presents our group's research on AI that thinks differently about how machines perceive, represent and reason over visual content. Drawing on years of work in digital health, environmental sensing and intelligent systems, I show that domain knowledge, structure-aware design and careful handling of noisy, real-world data are what turn accurate models into reliable, deployable ones. Building on this foundation, I present our recent efforts along four connected themes: efficient representation, where a "compress once, adapt many" paradigm allows a single compact encoding of video and 3D data to serve many downstream machine vision tasks; fine-grained understanding, where vision-language models are guided to link visual parts with semantic descriptions, even with few examples; spatio-temporal reasoning, where compact, task-aware video representations support efficient question answering; and authenticity, where structural cues are used to expose the subtle traces left by generative models in fake images. Together, these themes outline a path toward visual AI that is efficient, discriminative and trustworthy. I conclude with open challenges and opportunities for collaboration, including unified multimodal pipelines and emerging computing paradigms for imaging.
Biography:
Professor Manoranjan Paul is a Professor of Computer Science at Charles Sturt University, Director of its Computer Vision Lab, and Head of the Machine Vision and Digital Health Research Group. An award-winning researcher, he received the ACS ICT Researcher of the Year and Golden Disruptor awards in 2017. He has published around 200 peer-reviewed publications, supervised 16 PhD completions, and secured $3.6 million in competitive external research funding. He serves as an Associate Editor for leading IEEE and EURASIP journals and is a Senior Member of IEEE and ACS.
Agenda
5:30 pm — Welcome and IEEE SPS Chapter and speaker introductions
5:35 pm — Presentation by Professor Manoranjan Paul
6:15 pm — Questions and discussion
6:30 pm — Close