| Title |
Prekių ženklų reklamos efektyvumo vertinimas taikant giliojo mokymosi algoritmus analizuojant vaizdinę medžiagą |
| Translation of Title |
Evaluating brand advertising effectiveness using deep learning algorithms in visual material analysis. |
| Authors |
Gudauskas, Julius |
| Full Text |
|
| Pages |
75 |
| Keywords [eng] |
deep learning ; artificial intelligence ; object detection ; brands visibility |
| Abstract [eng] |
In the dynamic landscape of marketing and advertising, assessing brand visibility in live sports events plays a pivotal role in understanding brand exposure and impact. Traditional methods of manual annotation and analysis are time-consuming and subjective, necessitating automated solutions for efficient and objective evaluation. Although these decisions are highly relevant, there is a small amount of research that addresses open-ended advertising detection for both known and unknown brands. This study proposes a new method using a deep learning algorithm that can analyze live sports videos and provide brands visibility results. Open logo datasets were utilized for model training, along with a newly created and annotated dataset of brand advertisements from basketball game images. The experiments conducted provide detailed insights into the models' behavior and performance. |
| Dissertation Institution |
Kauno technologijos universitetas. |
| Type |
Master thesis |
| Language |
Lithuanian |
| Publication date |
2024 |
