Hierarchical Boundary-Aware Neural Encoder for Video Captioning

TL;DR

This paper introduces a hierarchical, boundary-aware LSTM encoder for video captioning that identifies segment boundaries to improve video representation and captioning accuracy.

Contribution

It proposes a novel LSTM cell that detects discontinuities in videos, enabling hierarchical encoding for better video understanding.

Findings

Improves state-of-the-art results on movie description datasets.

Effectively discovers hierarchical structures in videos.

Enhances video captioning accuracy across multiple datasets.

Abstract

The use of Recurrent Neural Networks for video captioning has recently gained a lot of attention, since they can be used both to encode the input video and to generate the corresponding description. In this paper, we present a recurrent video encoding scheme which can discover and leverage the hierarchical structure of the video. Unlike the classical encoder-decoder approach, in which a video is encoded continuously by a recurrent layer, we propose a novel LSTM cell, which can identify discontinuity points between frames or segments and modify the temporal connections of the encoding layer accordingly. We evaluate our approach on three large-scale datasets: the Montreal Video Annotation dataset, the MPII Movie Description dataset and the Microsoft Video Description Corpus. Experiments show that our approach can discover appropriate hierarchical representations of input videos and improve the state of the art results on movie description datasets.