Solving the visual symbol grounding problem has long been a goal of artificial intelligence. The field appears to be advancing closer to this goal with recent breakthroughs in deep learning for natural language grounding in static images. In this paper, we propose to translate videos directly to sentences using a unified deep neural network with both convolutional and recurrent structure. Described video datasets are scarce, and most existing methods have been applied to toy domains with a small vocabulary of possible words. By transferring knowledge from 1.2M+ images with category labels and 100,000+ images with captions, our method is able to create sentence descriptions of open-domain videos with large vocabularies. We compare our approach with recent work using language generation metrics, subject, verb, and object prediction accuracy, and a human evaluation.

PDF

In Proceedings the 2015 Conference of the North American Chapter of the Association for Computational Linguistics -- Human Language Technologies (NAACL HLT 2015), pp. 1494--1504, Denver, Colorado, June 2015.

@inproceedings{venugopalan:naacl15, title={Translating Videos to Natural Language Using Deep Recurrent Neural Networks}, author={Subhashini Venugopalan and Huijuan Xu and Jeff Donahue and Marcus Rohrbach and Raymond Mooney and Kate Saenko}, booktitle={Proceedings the 2015 Conference of the North American Chapter of the Association for Computational Linguistics -- Human Language Technologies (NAACL HLT 2015)}, month={June}, address={Denver, Colorado}, pages={1494--1504}, url="http://www.cs.utexas.edu/users/ai-labpub-view.php?PubID=127495", year={2015} }

Slides (PDF)