SUN-Spot: An RGB-D Dataset With Spatial Referring Expressions

Cecilia Mauceri, Martha Palmer, Christoffer Heckman; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 0-0

Abstract


We introduce a new dataset, SUN-Spot, for localizing objects using spatial referring expressions (REs). SUN-Spot is the only RE dataset which uses RGB-D images. It also contains a greater average number of spatial prepositions and more cluttered scenes than previous RE datasets. Using a simple baseline, we show that including a depth channel in RE models can improve performance on both generation and comprehension.

Related Material


[pdf]
[bibtex]
@InProceedings{Mauceri_2019_ICCV,
author = {Mauceri, Cecilia and Palmer, Martha and Heckman, Christoffer},
title = {SUN-Spot: An RGB-D Dataset With Spatial Referring Expressions},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2019}
}