Dutt, Varun and Galan, Lucas and Doctor, Faiyaz and Barakat, Lina and Isaacs, Kate and Hadjigeorgiou, Demetris and Fumagalli, Aldo (2024) An AI Driven Pipeline for 6G Enabled Digital Creatives Identification, Performance Monitoring and Attribution. In: The 24th IEEE/ACM international Symposium on Cluster, Cloud and Internet Computing (CCGRID), 2024-05-06 - 2024-07-09, Philadelphia, USA. (In Press)
Dutt, Varun and Galan, Lucas and Doctor, Faiyaz and Barakat, Lina and Isaacs, Kate and Hadjigeorgiou, Demetris and Fumagalli, Aldo (2024) An AI Driven Pipeline for 6G Enabled Digital Creatives Identification, Performance Monitoring and Attribution. In: The 24th IEEE/ACM international Symposium on Cluster, Cloud and Internet Computing (CCGRID), 2024-05-06 - 2024-07-09, Philadelphia, USA. (In Press)
Dutt, Varun and Galan, Lucas and Doctor, Faiyaz and Barakat, Lina and Isaacs, Kate and Hadjigeorgiou, Demetris and Fumagalli, Aldo (2024) An AI Driven Pipeline for 6G Enabled Digital Creatives Identification, Performance Monitoring and Attribution. In: The 24th IEEE/ACM international Symposium on Cluster, Cloud and Internet Computing (CCGRID), 2024-05-06 - 2024-07-09, Philadelphia, USA. (In Press)
Abstract
In the growing creative marketing sector, a high volume of digital assets in the form of images and videos are often generated for various forms of advertising. It is critical to be able to track these assets back to the original high value photo and video shoots they are derived from as well as understanding in real-time how well they are performing and how they can be augmented to perform better in response to the needs and preferences of dynamic audiences. In this paper we propose a framework that leverages deep learning approaches that learns to match local features across images to tie master images to various derived digital assets. The proposed pipeline is further able to use audience responses to predict performances of assets with attribution mechanisms for analysing how the modification of asset features enhance or degrade performance. We finally discuss how 6G infrastructures would be used with the pipeline to facilitate real-time and dynamically responsive content intelligence.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Additional Information: | Published proceedings: _not provided_ |
Uncontrolled Keywords: | 6G infrastructures; Attribution Pipeline; Content Intelligence; Creative Asset Tracking; Deep Feature Extractors; Diffusion Models; Performance Analyses; Transformers |
Divisions: | Faculty of Science and Health Faculty of Science and Health > Computer Science and Electronic Engineering, School of |
SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
Depositing User: | Unnamed user with email elements@essex.ac.uk |
Date Deposited: | 03 Oct 2024 12:08 |
Last Modified: | 11 Dec 2024 18:24 |
URI: | http://repository.essex.ac.uk/id/eprint/38707 |
Available files
Filename: CCGRIDCloud6GWorkshopPaper2024_Final.pdf