Scaling Up Video Summarization Pretraining with Large Language Models

arXiv:2404.03398v1 Announce Type: new
Abstract: Long-form video content constitutes a significant portion of internet traffic, making automated video summarization an essential research problem. However, existing video summarization datasets are notably limited in their size, constraining the effectiveness of state-of-the-art methods for generalization. Our work aims to overcome this limitation by capitalizing on the abundance of long-form videos with dense speech-to-video alignment and the remarkable capabilities of recent large language models (LLMs) in summarizing long text. We introduce an automated and …

abstract art arxiv automated cs.cv datasets form however internet language language models large language large language models making pretraining research scaling scaling up state summarization traffic type video work