Accession Number:

AD1049685

Title:

Improving LSTM-based Video Description with Linguistic Knowledge Mined from Text

Descriptive Note:

Journal Article - Open Access

Corporate Author:

NATIONAL SCIENCE FOUNDATION ARLINGTON VA ARLINGTON United States

Report Date:

2016-11-29

Pagination or Media Count:

6.0

Abstract:

This paper investigates how linguistic knowledge mined from large text corpora can aid the generation of natural language descriptions of videos. Specifically, we integrate both a neural language model and distributional semantic strained on large text corpora into a recent LSTM-based architecture for video description. We evaluate our approach on a collection of Youtube videos as well as two large movie description datasets showing significant improvements in grammaticality while modestly improving descriptive quality.

Subject Categories:

Distribution Statement:

APPROVED FOR PUBLIC RELEASE