Understanding and Predicting the Memorability of Outdoor Natural Scenes
arXiv:1810.06679 · doi:10.1109/TIP.2020.2975957
Abstract
Memorability measures how easily an image is to be memorized after glancing, which may contribute to designing magazine covers, tourism publicity materials, and so forth. Recent works have shed light on the visual features that make generic images, object images or face photographs memorable. However, these methods are not able to effectively predict the memorability of outdoor natural scene images. To overcome this shortcoming of previous works, in this paper, we provide an attempt to answer: "what exactly makes outdoor natural scenes memorable". To this end, we first establish a large-scale outdoor natural scene image memorability (LNSIM) database, containing 2,632 outdoor natural scene images with their ground truth memorability scores and the multi-label scene category annotations. Then, similar to previous works, we mine our database to investigate how low-, middle- and high-level handcrafted features affect the memorability of outdoor natural scenes. In particular, we find that the high-level feature of scene category is rather correlated with outdoor natural scene memorability, and the deep features learnt by deep neural network (DNN) are also effective in predicting the memorability scores. Moreover, combining the deep features with the category feature can further boost the performance of memorability prediction. Therefore, we propose an end-to-end DNN based outdoor natural scene memorability (DeepNSM) predictor, which takes advantage of the learned category-related features. Then, the experimental results validate the effectiveness of our DeepNSM model, exceeding the state-of-the-art methods. Finally, we try to understand the reason of the good performance for our DeepNSM model, and also study the cases that our DeepNSM model succeeds or fails to accurately predict the memorability of outdoor natural scenes. Code: github.com/JiaxinLu-home/Natural-Scene-Memorability-Dataset.
arXiv commentAdded links to dataset and code; Modified footnote 6 in experiments. arXiv admin note: text overlap with arXiv:1808.08754
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- Object Detectors Emerge in Deep Scene CNNs
- Deep Visual Attention Prediction
- Reducing Complexity of HEVC: A Deep Learning Approach
- Predicting Head Movement in Panoramic Video: A Deep Reinforcement Learning Approach
- Salient Object Detection in the Deep Learning Era: An In-Depth Survey
- What Makes Natural Scene Memorable?