Distinctive-attribute Extraction for Image Captioning

Boeun Kim, Young Han Lee, Hyedong Jung, Choongsang Cho; Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018, pp. 0-0

Abstract


Image captioning has evolved with the progress of deep neural networks. However, generating qualitatively detailed and distinctive captions is still an open issue. In previous works, a caption involving semantic description can be generated by applying additional information into the RNNs. In this approach, we propose a distinctive-attribute extraction (DaE) method that extracts attributes which explicitly encourage RNNs to generate an accurate caption. We evaluate the proposed method with a challenge data and verify that this method improves the performance, describing images in more detail. The method can be plugged into various models to improve their performance.

Related Material


[pdf]
[bibtex]
@InProceedings{Kim_2018_ECCV_Workshops,
author = {Kim, Boeun and Han Lee, Young and Jung, Hyedong and Cho, Choongsang},
title = {Distinctive-attribute Extraction for Image Captioning},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV) Workshops},
month = {September},
year = {2018}
}