Workshop Title:

Enhancing Video Understanding with Advanced NLP Algorithms for Advertising

Date:

May 23rd, 2023 (GMT+1)

Organizer:

Department of Computer and Information Sciences, University of Strathclyde

Keywords:

• NLP
• Video Understanding
• Video Advertising
• Linear Advertising
• Video Streaming

Workshop Chair:

Personal Bio:

Prof. Anil Fernando received the B.Sc. (Hons.) degree (First Class) in electronics and telecommunication engineering from the University of Moratuwa, Sri Lanka, in 1995, and the M.Sc. in Communications (Distinction) from the Asisan Institute of Technology, Bangkok, Thailand in 1997 and Ph.D. in Computer Science (Video Coding and Communications) from the University of Bristol, UK in 2001. He is a professor in Video Coding and Communications at the Department of Computer and Information Sciences, University of Strathclyde, UK. He leads the video coding and communication research team at Strathclyde. He has worked on major national and international multidisciplinary research projects and led most of them. He has published over 400 papers in international journals and conference proceedings and published a book on 3D video broadcasting. He has been working with all major EU broadcasters, BBC, and major European media companies/SMEs in the last decade in providing innovative media technologies for British and EU citizens. His main research interests are in Video coding and Communications, Machine Learning (ML) and Artificial Intelligence (AI), Semantic Communications, Signal Processing, Networking and Communications, Interactive Systems, Resource Optimizations in 6G, Distributed Technologies, Media Broadcasting and Quality of Experience (QoE).

Workshop Committee Members:

Mr. Waruna Silva, Researcher, orthalange.de-silva@strath.ac.uk

Workshop Description:

Background:

Effective tactics for audience reach and engagement are needed since video advertising is growing so quickly. The removal of cookies, however, makes it challenging to track user behavior and customize adverts to preferences. Natural Language Processing (NLP) algorithms, which scan video data and extract significant keywords and subjects, offer a powerful response. Streaming video advertising makes it challenging to understand context and meaning, which reduces the accuracy required for accurate targeting. This looks at ways to overcome these challenges by enhancing NLP algorithms. By increasing video context interpretation and meaning extraction, advertisers may be able to deliver more individualized and engaging advertisements in order to get over the limitations imposed by the removal of cookies.

Goal/Rationale:

The purpose of the workshop proposal is to explore the complexities of NLP algorithms in the context of streaming video advertising with the ultimate objective of overcoming their present drawbacks. This aims to foster an environment favorable to insightful discussions and fruitful collaborations among researchers' experts by carefully examining and evaluating the most recent developments in NLP algorithms, particularly in the areas of context and meaning extraction.

The primary goal of this is to explore approaches and techniques that have the potential to significantly improve the precision and effectiveness of NLP algorithms, particularly when it comes to understanding video context and deriving valuable insights from it. This aims to open up new opportunities and pave the way for more refined and sophisticated approaches to video advertising by addressing the gaps and obstacles currently present in this industry.

Scope and Information for Participants:

In the context of streaming video advertising, this seeks to present a thorough breadth of Natural Language Processing (NLP) algorithms. The focus includes an overview of NLP algorithms applied in this field and an examination of their uses and advantages. The workshop will also point out the constraints and difficulties associated with deriving context and meaning from video footage. The study will explore cutting-edge strategies and techniques that help to create more precise NLP algorithms by examining recent research developments. Through careful study, the performance of improved NLP algorithms in video context extraction will be assessed. Additionally, this will assess the effects of cookie removal, consider the implications for future streaming video advertising, and investigate alternative solutions to the challenges associated with personalized targeting in this evolving landscape.

Highlights:

The study's objective is to use topic modelling techniques to enhance contextual advertising. In specifically, the most current Transformer model and the classic Latent Dirichlet Allocation (LDA), probabilistic model are contrasted. In order to better target advertisements, it will be evaluated how well relevant subjects may be extracted from textual data.

In the research, the concept of efficient exploitability mapping which requires mapping the identified subjects to an industry-specific taxonomy is also discussed. This mapping method aims to increase ad relevancy and target audience targeting by matching the extracted subjects with relevant categories and concepts within the industry.

The study compares the advantages and disadvantages of LDA and the Transformer model in terms of topic extraction and contextual comprehension. The methodology chosen by this study produces more accurate and informative data, resulting in better contextual advertising campaigns.

The study emphasizes how important it is to relate these extracted topics to industrial taxonomy. Advertisers are better able to connect their advertisements with particular industrial sectors with the use of this mapping, ensuring that the proper audiences see them and that they have the greatest impact.

Access to Workshop:

CONF-MSS 2023 Workshop -- Glasgow (1) - YouTube

CONF-MSS 2023 Workshop -- Glasgow (2) - YouTube

Venue:

University of Strathclyde, Glasgow, G1 1XQ, UK.

VISA:

Welcome to GOV.UK (www.gov.uk)

What you need to do

• Check if what you plan to do in the UK is allowed as a Standard Visitor.
• Check if you meet the eligibility requirements.
• Check if you need to apply for a visa to visit the UK.
• Apply for a Standard Visitor visa online - if you need one.

Check you meet the eligibility requirements
You must have a passport or travel document to enter the UK. It should be valid for the whole of your stay.

You must be able to show that:

• you'll leave the UK at the end of your visit
• you're able to support yourself and your dependants during your trip (or have funding from someone else to support you)
• you're able to pay for your return or onward journey (or have funding from someone else to pay for the journey)
• you'll not live in the UK for extended periods through frequent or successive visits, or make the UK your main home

Check if you need a visa to visit the UK

Depending on your nationality, you'll either:

• have to apply for a Standard Visitor visa before you travel to the UK
• be able to visit the UK for up to 6 months without needing a visa

You can check if you need a visa before you apply.
If you do not need a visa, you must still meet the Standard Visitor eligibility requirements to visit the UK. You may be asked questions at the UK border about your eligibility and the activities you plan to do.