Close
Online Seminar | Towards more efficient video compression and enhancement with machine learning
29 July 2020, 11:30 am–12:30 pm
Lead R&D Engineer at the BBC, Marta Mrak showcases work being undertaken to exploit Machine Learning for the compression and enhancement of video, exploring the importance of breaking such systems out of the 'black-box'
This event is free.
Event Information
Open to
- All | UCL staff | UCL students
Availability
- Yes
Cost
- Free
Organiser
-
Robert Thompson – Institute of Communications and Connected Systems
Towards more efficient video compression and enhancement with machine learning
Machine learning techniques for more efficient video compression and video enhancement have been developed thanks to breakthroughs in deep learning. The new techniques, considered as an advanced form of Artificial Intelligence (AI), bring previously unforeseen capabilities. However, they typically come in the form of resource-hungry black-boxes (overly complex with little transparency regarding the inner workings). Their application can, therefore, be unpredictable and generally unreliable for large-scale use (e.g. in live broadcast).
The aim of the talk is to showcase work that illustrates how understanding the inner workings of Machine Learning (ML) applications can facilitate optimisation of learned models in video processing applications. This means that systems that incorporate them can be used in a more trustworthy manner. The talk introduces principles for simplification of learned models targeting improved transparency in implementing machine learning for video production and distribution applications. These principles are demonstrated on video compression examples, showing how bitrate savings and reduced complexity can be achieved by simplifying relevant deep learning models.
ICCS Chair
This session will be chaired by: Dr Laura Toni,
Attending the seminar
The Seminar will be held on the Zoom platform. Details of how to access Zoom can be found on their website.
Please click this URL to join. https://zoom.us/j/97399330909
Webinar ID: 973 9933 0909
Password: Will be distributed to ICCS members, others are welcome to join and the password can be requested by email iccs@ucl.ac.uk
About the Speaker
Dr Marta Mrak
Lead R&D Engineer at BBC R&D
Dr Marta Mrak (Dipl. Ing.and MSc EE, University of Zagreb, Croatia; PhD, Queen Mary University of London, UK) is a Lead R&D Engineer at BBC R&D and an Honorary Professor at Queen Mary University of London (QMUL), Multimedia and Vision Research Group. Within the IEEE, she is the Chair of Technical Committee on Multimedia Signal Processing, and elected member of IEEE Circuits and Systems Society’s Technical Committee on Multimedia Systems and Applications. Her research is focused on video compression fundamentals, new content experiences and data analytics. Marta serves as General Co-Chair of IEEE ICME 2020 and was the Lead TPC Chair for IEEE ICME 2019. She has organised numerous workshops and special sessions at conferences, in addition to special issues in journals. During 2013-2018, Marta was an Area Editor for Signal Processing Image Communication journal. She was also appointed as Associate Editor for IEEE Trans. on Multimedia in 2018, and an Associate Editor for IEEE Trans. on Image Processing in 2019.
More about Dr Marta Mrak