Generation and Comprehension of Unambiguous Object Descriptions

TitleGeneration and Comprehension of Unambiguous Object Descriptions
Publication TypeConference Paper
Year of Publication2016
AuthorsMao, J, Huang, J, Toshev, A, Camburu, O, Yuille, A, Murphy, K
Conference NameThe Conference on Computer Vision and Pattern Recognition (CVPR)
Date Published06/2016
Conference LocationLas Vegas, Nevada

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


We have released the dataset and a toolbox for visualization and evaluation, see \url{}.

URL mjhucla/Google_Refexp_toolbox

Research Area: 

CBMM Relationship: 

  • CBMM Funded