The School of Computer Science is pleased to present…
Exploration of Low-Level Features for Enhancing Movie Recommendation Systems
MSc Thesis Proposal by: Jasmin Patel
Date: 3rd July, 2024
Time: 9:30 am
Location: Essex Hall, Room 122
Abstract: We present a hybrid recommendation framework that employs detection models, such as YOLOv8, to identify and low-level catalog objects within movies, creating an item-item similarity matrix of movies. Our methodology involves constructing vectors from the frequency of detected objects within films, which are then used to determine the similarity between different movies. We also fetch the video transcripts to extract relevant features using LLMs. By integrating this information with a Top-N recommendation algorithm, we aim to provide users with suggestions that align with their interests.
Our method has the ability to tackle challenges in video recommendation, including the cold-start problem for new or metadata-sparse content. By autonomously analyzing the visual and aural elements of the movies, our system is capable of providing meaningful recommendations, even in the absence of movie metadata, which is a common occurrence on content platforms such as YouTube. With intersection of computer vision, recommender systems and LLMs, incorporating low-level features extracted from movies significantly enhances the precision of recommendations, suggesting a promising direction for further developments in recommendation systems. In addition, we plan to make the extracted object dataset available to the public for further research and to promote computational efficiency, which can be beneficial for the environment.
Keywords: Movie Recommended System, Object Detection, Computer Vision, Top-N Algorithm, Low-Level Features, Large Language Models (LLMs)
Thesis Committee:
Internal Reader: Dr. Ikjot Saini
External Reader: Dr. Mohammad Hassanzadeh
Advisor: Dr. Luis Rueda