Date of Submission

Fall 2023

Academic Program

Computer Science

Project Advisor 1

Rose Sloan

Project Advisor 2

Sven Anderson

Abstract/Artist's Statement

In recent years, the application of machine learning methodology into event detection has become increasingly prevalent, with examples ranging from surveillance to entertainment and healthcare. This project aims to explore the classification of events in video content with practical implication of content management and archival. To develop a method for event detection, we will utilize the VidLife dataset — a dataset that captures a wide array of life events from the popular American television sitcom series 'The Big Bang Theory'. This project focuses on the development of a hybrid model that combines Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) networks. To interpret sequential data effectively, we have chosen this combination to capture the spatial and temporal characteristics. The project’s focus is on the challenges involved in accurately identifying and classifying diverse life events in videos, showcasing the potential of machine learning in transforming how we analyze complex video data and explore different applications where automatic video categorization is necessary.

Open Access Agreement

Open Access

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

This work is protected by a Creative Commons license. Any use not permitted under that license is prohibited.