Summarizing Videos with Attention
arXiv:1812.01969
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.
arXiv commentPresented at ACCV2018 AIU2018 workshop
References in corpus (8)
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Convolutional Sequence to Sequence Learning
- A Structured Self-attentive Sentence Embedding
- Recurrent Models of Visual Attention
- Feature Representation in Convolutional Neural Networks
- Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward
- Video Summarization with Attention-Based Encoder-Decoder Networks
- Reflections on Shannon Information: In search of a natural information-entropy for images