Summarizing Videos with Attention [article]

Jiri Fajtl, Hajar Sadeghi Sokeh, Vasileios Argyriou, Dorothy Monekosso, Paolo Remagnino
2019 arXiv   pre-print
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
more » ... h 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.
arXiv:1812.01969v2 fatcat:5kzfj6ne2fa3tdywbs776dblf4