English

Summarizing Videos with Attention

Computer Vision and Pattern Recognition 2019-02-22 v2 Computation and Language Machine Learning

Abstract

In this work we propose a novel method for supervised, keyshots based video summarization by applying a conceptually simple and computationally efficient soft, self-attention mechanism. Current state of the art methods leverage bi-directional recurrent networks such as BiLSTM combined with attention. These networks are complex to implement and computationally demanding compared to fully connected networks. To that end we propose a simple, self-attention based network for video summarization which performs the entire sequence to sequence transformation in a single feed forward pass and single backward pass during training. Our method sets a new state of the art results on two benchmarks TvSum and SumMe, commonly used in this domain.

Keywords

Cite

@article{arxiv.1812.01969,
  title  = {Summarizing Videos with Attention},
  author = {Jiri Fajtl and Hajar Sadeghi Sokeh and Vasileios Argyriou and Dorothy Monekosso and Paolo Remagnino},
  journal= {arXiv preprint arXiv:1812.01969},
  year   = {2019}
}

Comments

Presented at ACCV2018 AIU2018 workshop

R2 v1 2026-06-23T06:32:38.368Z