Improving LSTM-based Video Description with Linguistic Knowledge Mined from Text (2016)
Subhashini Venugopalan, Lisa Anne Hendricks, Raymond Mooney, and Kate Saenko
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 semantics trained 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.
In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP-16), pp. 1961--1966, Austin, Texas 2016.

Raymond J. Mooney Faculty mooney [at] cs utexas edu
Subhashini Venugopalan Ph.D. Student vsub [at] cs utexas edu