Generation and Comprehension of Unambiguous Object Descriptions
Authors:
- Junhua MaoJMJunhua Mao
- Jonathan HuangJHJonathan Huang
- Alexander ToshevATAlexander Toshev
- Oana CamburuOCOana Camburu
- Alan YuilleAYAlan Yuille
- Kevin MurphyKMKevin Murphy
Top Cited Papers
- 1 June 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11-20
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 MSCOCO. We have released the dataset and a toolbox for visualization and evaluation, see https://github.com/ mjhucla/Google_Refexp_toolbox.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Visual Turing test for computer vision systemsProceedings of the National Academy of Sciences, 2015
- From the Virtual to the RealWorld: Referring to Objects in Real-World Spatial Scenes2015
- ImageSpiritACM Transactions on Graphics, 2014
- Scalable Object Detection Using Deep Neural Networks2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- ReferItGame: Referring to Objects in Photographs of Natural Scenes2014
- Computational Generation of Referring Expressions: A SurveyComputational Linguistics, 2012
- The segmented and annotated IAPR TC-12 benchmarkComputer Vision and Image Understanding, 2010
- Maximum mutual information estimation of hidden Markov model parameters for speech recognition2005
- Understanding natural languageCognitive Psychology, 1972