Seminars will take place via Microsoft Teams, with a meeting link to be shared via the seminar-announce emails. Unless otherwise stated, from 15.00 to 16.00 on Friday afternoons during semester time, followed by informal discussions.
| Date | Speaker | Title/Abstract |
|---|---|---|
| Friday 18 September |
||
| Friday 25 September |
Dr. Mohamed Elawady, CSM, University of Stirling | Reflection Symmetry Detection in 2D Images Abstract: Symmetry is a fundamental principle of visual perception to feel the equally distributed weights within foreground objects inside an image. It is used as a significant visual feature through various computer vision applications (i.e. object detection and segmentation), plus as an important composition measure in the art domain (i.e. aesthetic analysis). The development of symmetry detection has been improving rapidly since last century. In this work, the main objective is detecting reflection symmetry inside real-world images in a global scale. This method wins a recent symmetry competition worldwide in single and multiple cases. In summary, the spatial and context information of each candidate axis inside an image can be used as a local or global symmetry measure for further image analysis and scene understanding purposes. Bio: Mohamed Elawady is a new appointed university lecturer in data science, Stirling university. He was a lead computer vision researcher at a parisian startup: Qopius. He has studied in different European universities: PhD in computer vision at Hubert Curien laboratory, Lyon university [France] (2014-2019). European masters in vision and robotics (VIBOT) with Erasmus Mundus scholarship at Burgundy university [France], Girona university [Spain] and Heriot-Watt university [UK] (2012-2014). In addition, he is the winner of 2D reflection symmetry competitions (among participants) in ICCV’17 workshop: Detecting symmetry in the wild. |
| Friday 2 October |
||
| Friday 9 October |
||
| Friday 16 October |
||
| Friday 23 October |
||
| Friday 30 October |
Reading Week | |
| Friday 6 November |
No seminar this week | |
| Friday 13 November |
Dr Vahid Akbari, CSM, University of Stirling | Machine Learning and Big Data Meet Synthetic Aperture Radar (SAR) Change detection, classification, and object detection are very important for many applications of remotely sensed data from space- and air-borne instruments. Especially synthetic aperture (SAR) data are useful due to their all-weather capabilities. My major Focus in the last 12 years has been mainly on the algorithm development in machine learning and statistical modeling in interferometric and polarimetric SAR from satellite, and aircraft sensors for studies of land deformation, land cover classification, and change detection, as well as, marine target detection and characterization in polar regions and forest monitoring. In this presentation, I will give some of my research outputs highlighting where SAR might meet machine learning and big data. There will be seven major areas in my presentation:
|
| Friday 20 November |
Dr. Carles Barril, Department of Mathematics, Universitat Autonoma de Barcelona | Basic reproduction number for an age of infection epidemic model Abstract: In this talk we show how to define the basic reproduction number (the so-called R0) in continuously structured populations and, in particular, in an epidemic in which individuals are structured by the age of infection and distributed between asymptomatic and symptomatic. We consider an example of application to data of the crucial moment of the epidemic of the Covid-19 in Spain. |
| Friday 27 November |
Virtual Graduation for Postgraduates |
|
| Friday 4 December |
Prof. Bruce Graham, CSM, University of Stirling | Two pathway signalling processing in the brain Cortical pyramidal cells (PCs) have evolved to process two separate streams of driving input and to process them separately before they combine to generate an output from the cell. Thus we can regard such neurons as 2-point processors. This is quite unlike typical neurons in artificial neural networks, which treat all inputs equally and thus function as single point processors. In this talk we will consider the what, how and why of these inputs: what the two streams are, how they are combined in PCs and what it means for information processing in the cortex. |
Top image: Evolution of sounds by crowd-sourcing, from Brownlee, A. E. I., Kim, S-J., Wan, S-H., Chan, S. & Lawson, J. A. Crowd-Sourcing the Sounds of Places with a Web-Based Evolutionary Algorithm. Companion Proc. of the Genetic and Evolutionary Computation COnference 2019, Prague, Czech Republic, pp 131-132. DOI:10.1145/3319619.3322028