Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2018 | 10.18653/v1/d18-1436 | EMNLP |
DocType | Volume | Citations |
Conference | abs/1808.10584 | 0 |
PageRank | References | Authors |
0.34 | 21 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Harsh Jhamtani | 1 | 19 | 6.51 |
Taylor Berg-Kirkpatrick | 2 | 554 | 35.93 |