Modeling Context Between Objects for Referring Expression Understanding
This work addresses the challenge of grounding referring expressions in images for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of understanding referring expressions by modeling context between objects, showing that this approach outperforms methods that only consider object properties on Google RefExp and UNC RefExp datasets.
Referring expressions usually describe an object using properties of the object and relationships of the object with other objects. We propose a technique that integrates context between objects to understand referring expressions. Our approach uses an LSTM to learn the probability of a referring expression, with input features from a region and a context region. The context regions are discovered using multiple-instance learning (MIL) since annotations for context objects are generally not available for training. We utilize max-margin based MIL objective functions for training the LSTM. Experiments on the Google RefExp and UNC RefExp datasets show that modeling context between objects provides better performance than modeling only object properties. We also qualitatively show that our technique can ground a referring expression to its referred region along with the supporting context region.