期刊
出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3177745
关键词
Saliency; visual saliency prediction; image captioning; deep learning
类别
资金
- Citta educante of the National Technological Cluster on Smart Communities (Italian Ministry of Education, University and Research - MIUR) [CTN01_00034_393801]
- project JUMP - Una piattaforma sensoristica avanzata per rinnovare la pratica e la fruizione dello sport, del benessere, della riabilitazione e del gioco educativo - Emilia-Romagna region within the POR-FESR program
- CINECA award under the ISCRA initiative
- NVIDIA Corporation
Image captioning has been recently gaining a lot of attention thanks to the impressive achievements shown by deep captioning architectures, which combine Convolutional Neural Networks to extract image representations and Recurrent Neural Networks to generate the corresponding captions. At the same time, a significant research effort has been dedicated to the development of saliency prediction models, which can predict human eye fixations. Even though saliency information could be useful to condition an image captioning architecture, by providing an indication of what is salient and what is not, research is still struggling to incorporate these two techniques. In this work, we propose an image captioning approach in which a generative recurrent neural network can focus on different parts of the input image during the generation of the caption, by exploiting the conditioning given by a saliency prediction model on which parts of the image are salient and which are contextual. We show, through extensive quantitative and qualitative experiments on large-scale datasets, that our model achieves superior performance with respect to captioning baselines with and without saliency and to different state-of-the-art approaches combining saliency and captioning.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据