Issue No. 04 - April (2017 vol. 39)
Oriol Vinyals , Department of Research, Google, Mountain View, CA
Alexander Toshev , Department of Research, Google, Mountain View, CA
Samy Bengio , Department of Research, Google, Mountain View, CA
Dumitru Erhan , Department of Research, Google, Mountain View, CA
Automatically describing the content of an image is a fundamental problem in artificial intelligence that connects computer vision and natural language processing. In this paper, we present a generative model based on a deep recurrent architecture that combines recent advances in computer vision and machine translation and that can be used to generate natural sentences describing an image. The model is trained to maximize the likelihood of the target description sentence given the training image. Experiments on several datasets show the accuracy of the model and the fluency of the language it learns solely from image descriptions. Our model is often quite accurate, which we verify both qualitatively and quantitatively. Finally, given the recent surge of interest in this task, a competition was organized in 2015 using the newly released COCO dataset. We describe and analyze the various improvements we applied to our own baseline and show the resulting performance in the competition, which we won
ex-aequo with a team from Microsoft Research.
Logic gates, Training, Recurrent neural networks, Visualization, Computer vision, Computational modeling, Natural languages
O. Vinyals, A. Toshev, S. Bengio and D. Erhan, "Show and Tell: Lessons Learned from the 2015 MSCOCO Image Captioning Challenge," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 39, no. 4, pp. 652-663, 2017.