@conference {1983, title = {Generation and Comprehension of Unambiguous Object Descriptions}, booktitle = {The Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2016}, month = {06/2016}, address = {Las Vegas, Nevada}, abstract = {
We propose a method that can generate an unambiguous description (known as a referring expression) of a specific object or region in an image, and which can also comprehend or interpret such an expression to infer which object is being described.
We show that our method outperforms previous methods that generate descriptions of objects without taking into account other potentially ambiguous objects in the scene.
Our model is inspired by recent successes of deep learning methods for image captioning, but while image captioning is difficult to evaluate,  our task allows for easy objective evaluation.
We also present a new large-scale dataset for referring expressions, based on
MS-COCO.
We have released the dataset and a toolbox for visualization and evaluation, see \url{https://github.com/mjhucla/Google_Refexp_toolbox}.
}, url = {https://github.com/ mjhucla/Google_Refexp_toolbox}, author = {Junhua Mao and Jonathan Huang and Alexander Toshev and Oana Camburu and Alan Yuille and Kevin Murphy} }