Guiding the Long-Short Term Memory Model for Image Caption Generation

Xu Jia, Efstratios Gavves, Basura Fernando, Tinne Tuytelaars; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015, pp. 2407-2415

Abstract


In this work we focus on the problem of image caption generation. We propose an extension of the long short term memory (LSTM) model, which we coin gLSTM for short. In particular, we add semantic information extracted from the image as extra input to each unit of the LSTM block, with the aim of guiding the model towards solutions that are more tightly coupled to the image content. Additionally, we explore different length normalization strategies for beam search to avoid bias towards short sentences. On various benchmark datasets such as Flickr8K, Flickr30K and MS COCO, we obtain results that are on par with or better than the current state-of-the-art.

Related Material


[pdf]
[bibtex]
@InProceedings{Jia_2015_ICCV,
author = {Jia, Xu and Gavves, Efstratios and Fernando, Basura and Tuytelaars, Tinne},
title = {Guiding the Long-Short Term Memory Model for Image Caption Generation},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2015}
}