Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention
arXiv:1706.08474
Abstract
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 performances with respect to captioning baselines with and without saliency, and to different state of the art approaches combining saliency and captioning.
arXiv commentACM Transactions on Multimedia Computing, Communications and Applications, Vol. 14, No. 2, Article 48
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- SalGAN: Visual Saliency Prediction with Generative Adversarial Networks
- DeepGaze II: Reading fixations from deep features trained on object recognition
- Image Captioning with Semantic Attention
- Shallow and Deep Convolutional Networks for Saliency Prediction
- Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing
- Seeing with Humans: Gaze-Assisted Neural Image Captioning
- Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training
- A Deep Spatial Contextual Long-term Recurrent Convolutional Network for Saliency Detection