Video Summarization with Attention-Based Encoder-Decoder Networks

TL;DR

This paper introduces AVS, an attention-based encoder-decoder neural network for supervised video summarization, which effectively learns to select keyshots by mimicking human summarization through sequence-to-sequence modeling.

Contribution

It proposes a novel AVS framework utilizing BiLSTM and attention mechanisms for improved video summarization performance.

Findings

AVS outperforms state-of-the-art methods on SumMe and TVSum datasets.

Achieves 0.8% to 3% improvement in keyshot selection accuracy.

Demonstrates the effectiveness of attention mechanisms in video summarization.

Abstract

This paper addresses the problem of supervised video summarization by formulating it as a sequence-to-sequence learning problem, where the input is a sequence of original video frames, the output is a keyshot sequence. Our key idea is to learn a deep summarization network with attention mechanism to mimic the way of selecting the keyshots of human. To this end, we propose a novel video summarization framework named Attentive encoder-decoder networks for Video Summarization (AVS), in which the encoder uses a Bidirectional Long Short-Term Memory (BiLSTM) to encode the contextual information among the input video frames. As for the decoder, two attention-based LSTM networks are explored by using additive and multiplicative objective functions, respectively. Extensive experiments are conducted on three video summarization benchmark datasets, i.e., SumMe, and TVSum. The results demonstrate the superiority of the proposed AVS-based approaches against the state-of-the-art approaches,with remarkable improvements from 0.8% to 3% on two datasets,respectively..