What Makes Natural Scene Memorable?
This work addresses the challenge of predicting memorability for natural scenes, which is incremental as it extends prior research on image memorability to a specific domain.
The paper tackled the problem of understanding and predicting natural scene memorability by building a large-scale database (LNSIM) and analyzing handcrafted features, finding that scene category is highly correlated with memorability, and proposed a deep neural network predictor (DeepNSM) that outperforms existing methods with a correlation coefficient of 0.68.
Recent studies on image memorability have shed light on the visual features that make generic images, object images or face photographs memorable. However, a clear understanding and reliable estimation of natural scene memorability remain elusive. In this paper, we provide an attempt to answer: "what exactly makes natural scene memorable". Specifically, we first build LNSIM, a large-scale natural scene image memorability database (containing 2,632 images and memorability annotations). Then, we mine our database to investigate how low-, middle- and high-level handcrafted features affect the memorability of natural scene. In particular, we find that high-level feature of scene category is rather correlated with natural scene memorability. Thus, we propose a deep neural network based natural scene memorability (DeepNSM) predictor, which takes advantage of scene category. Finally, the experimental results validate the effectiveness of DeepNSM.