Multi-scale hierarchical residual network for dense captioning

Yan Tian, Xun Wang, Jiachen Wu, Ruili Wang, Bailin Yang

Research output: Journal PublicationArticlepeer-review

23 Citations (Scopus)

Abstract

Recent research on dense captioning based on the recurrent neural network and the convolutional neural network has made a great progress. However, mapping from an image feature space to a description space is a nonlinear and multimodel task, which makes it difficult for the current methods to get accurate results. In this paper, we put forward a novel approach for dense captioning based on hourglass-structured residual learning. Discriminant feature maps are obtained by incorporating dense connected networks and residual learning in our model. Finally, the performance of the approach on the Visual Genome V1.0 dataset and the region labelled MS-COCO (Microsoft Common Objects in Context) dataset are demonstrated. The experimental results have shown that our approach outperforms most current methods.

Original languageEnglish
Pages (from-to)181-196
Number of pages16
JournalJournal of Artificial Intelligence Research
Volume64
DOIs
Publication statusPublished - 1 Jan 2019
Externally publishedYes

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Multi-scale hierarchical residual network for dense captioning'. Together they form a unique fingerprint.

Cite this