Learning to Describe Differences Between Pairs of Similar Images
This addresses the need for coherent multi-sentence generation in vision-language tasks, though it is incremental as it builds on existing methods with a new dataset and model.
The paper tackles the problem of automatically generating text to describe differences between pairs of similar images, using a crowd-sourced dataset from video-surveillance footage, and proposes a model that outperforms attention-based models in both single- and multi-sentence generation.
In this paper, we introduce the task of automatically generating text to describe the differences between two similar images. We collect a new dataset by crowd-sourcing difference descriptions for pairs of image frames extracted from video-surveillance footage. Annotators were asked to succinctly describe all the differences in a short paragraph. As a result, our novel dataset provides an opportunity to explore models that align language and vision, and capture visual salience. The dataset may also be a useful benchmark for coherent multi-sentence generation. We perform a firstpass visual analysis that exposes clusters of differing pixels as a proxy for object-level differences. We propose a model that captures visual salience by using a latent variable to align clusters of differing pixels with output sentences. We find that, for both single-sentence generation and as well as multi-sentence generation, the proposed model outperforms the models that use attention alone.