Despite its wide range of applications, video summarization is still held back by the scarcity of extensive datasets, largely due to the labor-intensive and costly nature of frame-level annotations. As a result, existing video summarization methods are prone to overfitting. To mitigate this challenge, we propose a novel self-supervised video representation learning method using knowledge distillation to pre-train a transformer encoder. Our method matches its semantic video representation, which is constructed with respect to frame importance scores, to a representation derived from a CNN trained on video classification. Empirical evaluations on correlation-based metrics, such as Kendall's τ and Spearman's ρ demonstrate the superiority of our approach compared to existing state-of-the-art methods in assigning relative scores to the input frames.
@article{arxiv.2303.15993,
title = {SELF-VS: Self-supervised Encoding Learning For Video Summarization},
author = {Hojjat Mokhtarabadi and Kave Bahraman and Mehrdad HosseinZadeh and Mahdi Eftekhari},
journal= {arXiv preprint arXiv:2303.15993},
year = {2023}
}