Improving LSTM-based Video Description with Linguistic Knowledge Mined from Text
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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Nov 29, 2016
- Accession Number
- AD1049685
Entities
People
- Kate Saenko
- Lisa Anne Hendricks
- Raymond Mooney
- Subhashini Venugopalan
Organizations
- National Science Foundation